Undermind - Research Engine

Research Topic

Assessment of AI-driven predictive models in early detection of sepsis in ICU patients. I want to look for studies evaluating the effectiveness and implementation challenges of AI models designed to predict sepsis onset in critically ill patients earlier than current clinical methods allow, to improve timely interventions and patient outcomes.

Summary

The literature search has yielded significant findings on AI-driven predictive models for the early detection of sepsis in ICU patients, with numerous studies demonstrating various machine learning techniques and their effectiveness in improving early detection and potentially enhancing patient outcomes [1, 3, 5, 6, 10, 12].

Papers such as [1] and [6] introduce AI models that utilize advanced neural network techniques and genetic algorithms, respectively, achieving high predictive accuracy and offering substantial improvements over traditional clinical methods by predicting sepsis several hours before onset. These results emphasize the potential of AI in transforming critical care by allowing earlier interventions.
Other notable studies [10, 12] validate their models with real-world ICU data, integrating AI systems within clinical workflows which not only underscores the practical applicability but also addresses critical implementation challenges, making these references pivotal for understanding both the effectiveness and operational integration of AI in clinical settings.

To understand the relationships and patterns within the papers found, see also:

Directly Relevant AI Studies for Early Sepsis Detection in ICU

Papers focused exclusively on the development and evaluation of AI models that predict sepsis earlier than traditional methods in ICU settings. References: [1, 5, 6, 10, 12, 13, 19, 31, 32, 47, 49, 50, 51, 57, 66, 77, 90, 91, 108]

Implementation and Effectiveness of AI-based Models

Studies that assess how AI models are integrated into clinical workflows and their effectiveness in real-world ICU settings. References: [8, 10, 13, 19, 22, 27, 37, 47, 58, 59, 72, 73, 75, 79, 84, 98, 114, 115]

Comparison of AI Models with Traditional Methods

Research comparing AI-driven sepsis detection models against common clinical scoring systems or other traditional methods in ICU. References: [11, 23, 24, 35, 36, 38, 40, 46, 51, 55, 64, 70, 78, 105, 117]

Broad Applications of AI in ICU Sepsis Detection

Papers discussing the general use of AI and machine learning technologies for sepsis prediction and other related medical applications in ICU settings. References: [28, 29, 44, 52, 53, 56, 60, 61, 63, 65, 71, 83, 86, 87, 88, 100, 103, 112]

So far, I've closely analyzed 640 of the most promising papers, and I've found ~276-320 that are relevant, which is probably ~67.7% of all that exist.

To get this estimate, we do a statistical analysis of the discovery process.

References

Last 5 years

Last 2 years

> 1 citation per year

> 5 citations per year

Topic Match

Cit./Year

Year

Paper

Paper Relevance Summary

98.3%

3.7

2020

[1] Bi-Directional Gated Recurrent Unit Based Ensemble Model for the Early Detection of Sepsis Sajila D. Wickramaratne and Md. Shaad Mahmud 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) 2020 - 15 citations - Show abstract - Cite 98.3% topic match

Introduces a GRU-based AI model for early sepsis detection. Achieves an AUROC of 0.97, predicting sepsis onset 6 hours early. Outperforms existing machine learning models and CDRs in precision and generalizability.

Introduces a GRU-based AI model for early sepsis detection. Achieves an AUROC of 0.97, predicting sepsis onset 6 hours early. Outperforms existing machine learning models and CDRs in precision and generalizability.

98.2%

10.6

2019

[2] The Signature-Based Model for Early Detection of Sepsis From Electronic Health Records in the Intensive Care Unit James Morrill, ..., and Terry Lyons 2019 Computing in Cardiology (CinC) 2019 - 52 citations - Show abstract - Cite 98.2% topic match

Develops an AI model for early sepsis detection in ICU. Utilizes signature-based regression and gradient boosting machine algorithm. Model ranked 1st in effectiveness, with a utility function score of 0.360.

Develops an AI model for early sepsis detection in ICU. Utilizes signature-based regression and gradient boosting machine algorithm. Model ranked 1st in effectiveness, with a utility function score of 0.360.

98.0%

72.6

2017

[3] An Interpretable Machine Learning Model for Accurate Prediction of Sepsis in the ICU S. Nemati, ..., and T. Buchman Critical Care Medicine 2017 - 483 citations - Show abstract - Cite Abstract: Objectives: Sepsis is among the leading causes of morbidity, mortality, and cost overruns in critically ill patients. Early intervention with antibiotics improves survival in septic patients. However, no clinically validated system exists for real-time prediction of sepsis onset. We aimed to develop and validate an Artificial Intelligence Sepsis Expert algorithm for early prediction of sepsis. Design: Observational cohort study. Setting: Academic medical center from January 2013 to December 2015. Patients: Over 31,000 admissions to the ICUs at two Emory University hospitals (development cohort), in addition to over 52,000 ICU patients from the publicly available Medical Information Mart for Intensive Care-III ICU database (validation cohort). Patients who met the Third International Consensus Definitions for Sepsis (Sepsis-3) prior to or within 4 hours of their ICU admission were excluded, resulting in roughly 27,000 and 42,000 patients within our development and validation cohorts, respectively. Interventions: None. Measurements and Main Results: High-resolution vital signs time series and electronic medical record data were extracted. A set of 65 features (variables) were calculated on hourly basis and passed to the Artificial Intelligence Sepsis Expert algorithm to predict onset of sepsis in the proceeding T hours (where T = 12, 8, 6, or 4). Artificial Intelligence Sepsis Expert was used to predict onset of sepsis in the proceeding T hours and to produce a list of the most significant contributing factors. For the 12-, 8-, 6-, and 4-hour ahead prediction of sepsis, Artificial Intelligence Sepsis Expert achieved area under the receiver operating characteristic in the range of 0.83–0.85. Performance of the Artificial Intelligence Sepsis Expert on the development and validation cohorts was indistinguishable. Conclusions: Using data available in the ICU in real-time, Artificial Intelligence Sepsis Expert can accurately predict the onset of sepsis in an ICU patient 4–12 hours prior to clinical recognition. A prospective study is necessary to determine the clinical utility of the proposed sepsis prediction model. 98.0% topic match

Provides an AI model for early sepsis prediction in ICU. The model uses vital signs and EMR data for real-time analysis. Evaluated using over 73,000 ICU admissions, emphasizing accuracy and interpretability.

Provides an AI model for early sepsis prediction in ICU. The model uses vital signs and EMR data for real-time analysis. Evaluated using over 73,000 ICU admissions, emphasizing accuracy and interpretability.

97.9%

6.0

2020

[4] Utilization of the Signature Method to Identify the Early Onset of Sepsis From Multivariate Physiological Time Series in Critical Care Monitoring James Morrill, ..., and Terry Lyons Critical Care Medicine 2020 - 24 citations - Show abstract - Cite 97.9% topic match

Develops a signature-based AI model for early sepsis detection in ICU patients. Model predicts sepsis by analyzing physiological data from over 60,000 ICU stays. Utilizes the Sepsis-3 criteria, highlighting a focus on early predictive capabilities and accuracy.

Develops a signature-based AI model for early sepsis detection in ICU patients. Model predicts sepsis by analyzing physiological data from over 60,000 ICU stays. Utilizes the Sepsis-3 criteria, highlighting a focus on early predictive capabilities and accuracy.

97.9%

0.0

2024

[5] Development and Validation of the VIOSync Sepsis Prediction Index: A Novel Machine Learning Model for Sepsis Prediction in ICU Patients S. G. Liliopoulos, ..., and I. A. Gkouzionis medRxiv 2024 - 0 citations - Show abstract - Cite Abstract: Background: Sepsis is the third leading cause of death worldwide and the main cause of in-hospital mortality. Despite decades of research, sepsis remains a major challenge faced by patients, clinicians, and medical systems worldwide. Early identification and prediction of patients at risk of sepsis and adverse outcomes associated with sepsis are critical. In this work, we aimed to develop an artificial intelligence algorithm that can predict sepsis early. Materials and Methods: We developed a predictive model for sepsis using data from the Physionet Cardiology Challenge 2019 ICU database. Our cohort consisted of adult patients who were admitted to the ICU. Sepsis diagnoses were determined using the Sepsis-3 criteria. The model, built with the XGBoost algorithm, was designed to anticipate sepsis prior to the appearance of clinical symptoms. An internal validation was conducted using a hold-off test dataset to evaluate the AI model's predictive performance. Results: We have developed the VIOSync Sepsis Prediction Index (SPI), an AI-based predictive model designed to forecast sepsis up to six hours before its clinical onset, as defined by Sepsis-3 criteria. The AI model, trained on a dataset comprising approximately 40,000 adult patients, integrates variables such as vital signs, laboratory data, and demographic information. The model demonstrated a high prediction accuracy rate of 97%, with a sensitivity of 87% and a specificity of 98% in predicting sepsis up to 6 hours before the onset. When compared to the established qSOFA score, which has a specificity of 89% for sepsis prediction, our VIOSync SPI algorithm significantly enhances predictive reliability, potentially reducing false positive rates by a factor of 5.5. Conclusions: The VIOSync SPI demonstrated superior prediction performance over current sepsis early warning scores and predictive algorithms for sepsis onset. To validate the generalizability of our method across populations and treatment protocols, external validation studies are essential. 97.9% topic match

Develops a novel AI model, VIOSync, for early sepsis prediction in ICU patients. Uses data from the Physionet Challenge 2019 ICU database for model training and validation. Targets early detection to improve intervention times and patient outcomes in sepsis management within ICU settings.

Develops a novel AI model, VIOSync, for early sepsis prediction in ICU patients. Uses data from the Physionet Challenge 2019 ICU database for model training and validation. Targets early detection to improve intervention times and patient outcomes in sepsis management within ICU settings.

97.8%

2.0

2022

[6] Early Prediction of Sepsis Onset Using Neural Architecture Search Based on Genetic Algorithms Jae Kwan Kim, ..., and Laehyun Kim International Journal of Environmental Research and Public Health 2022 - 5 citations - Show abstract - Cite 97.8% topic match

Proposes an AI model using NAS and genetic algorithms for early sepsis prediction in ICU. Evaluated on MIMIC-III data, predicting sepsis onset 3 hours before it occurs, with high accuracy. Outperforms traditional assessment tools (SOFA, qSOFA, SAPS) in predicting sepsis early.

Proposes an AI model using NAS and genetic algorithms for early sepsis prediction in ICU. Evaluated on MIMIC-III data, predicting sepsis onset 3 hours before it occurs, with high accuracy. Outperforms traditional assessment tools (SOFA, qSOFA, SAPS) in predicting sepsis early.

97.8%

4.7

2017

[7] Multiscale network representation of physiological time series for early prediction of sepsis S. Shashikumar, ..., and S. Nemati Physiological Measurement 2017 - 31 citations - Show abstract - Cite 97.8% topic match

Demonstrates AI-driven model for early sepsis prediction in ICU. Uses multiscale network of heart rate and blood pressure for prediction, increasing prediction accuracy by 20%. Compares AI-driven methods to traditional indices, emphasizing improvement and utilizes common clinical measurements.

Demonstrates AI-driven model for early sepsis prediction in ICU. Uses multiscale network of heart rate and blood pressure for prediction, increasing prediction accuracy by 20%. Compares AI-driven methods to traditional indices, emphasizing improvement and utilizes common clinical measurements.

97.8%

1.4

2019

[8] Convolutional and Recurrent Neural Networks for Early Detection of Sepsis Using Hourly Physiological Data from Patients in Intensive Care Unit Xin Li, ..., and F. Schlindwein 2019 Computing in Cardiology (CinC) 2019 - 7 citations - Show abstract - Cite 97.8% topic match

Provides an AI model for early sepsis detection in ICU patients. Utilizes CNN and RNN neural networks to predict sepsis 6-12 hours before clinical onset using physiological data. Achieved 90.6% accuracy, indicating potential for improving early sepsis intervention in critically ill patients.

Provides an AI model for early sepsis detection in ICU patients. Utilizes CNN and RNN neural networks to predict sepsis 6-12 hours before clinical onset using physiological data. Achieved 90.6% accuracy, indicating potential for improving early sepsis intervention in critically ill patients.

97.7%

0.0

2023

[9] SMOTE-TOMEK: A Hybrid Sampling-Based Ensemble Learning Approach for Sepsis Prediction M. Kumar, ..., and Vudavagandla Kushal 2023 2nd International Conference on Edge Computing and Applications (ICECAA) 2023 - 0 citations - Show abstract - Cite 97.7% topic match

Evaluates an AI model's effectiveness in early sepsis prediction. The model, using ensemble learning with SMOTE-TOMEK, predicts sepsis 48 hours in advance using vital signs. Highlights the tool's high sensitivity, specificity, and resilience to missing data for sepsis detection in ICU settings.

Evaluates an AI model's effectiveness in early sepsis prediction. The model, using ensemble learning with SMOTE-TOMEK, predicts sepsis 48 hours in advance using vital signs. Highlights the tool's high sensitivity, specificity, and resilience to missing data for sepsis detection in ICU settings.

97.7%

0.0

2023

[10] Development and Validation of Deep-Learning-Based Sepsis and Septic Shock Early Prediction System (DeepSEPS) Using Real-World ICU Data Taehwa Kim, ..., and Woo Hyun Cho Journal of Clinical Medicine 2023 - 0 citations - Show abstract - Cite 97.7% topic match

Develops DeepSEPS for early sepsis prediction in ICU. Uses deep learning on EMR data, outperforming traditional scoring systems. Validated with real-world data, highlighting improved early detection capabilities.

Develops DeepSEPS for early sepsis prediction in ICU. Uses deep learning on EMR data, outperforming traditional scoring systems. Validated with real-world data, highlighting improved early detection capabilities.

97.7%

16.5

2020

[11] The development an artificial intelligence algorithm for early sepsis diagnosis in the intensive care unit K. Yuan, ..., and Ray-Jade Chen International journal of medical informatics 2020 - 69 citations - Show abstract - Cite 97.7% topic match

97.6%

0.0

2023

[12] Development and validation of a machine learning model integrated with the clinical workflow for early detection of sepsis Mohammed A Mahyoub, ..., and Ajit Shukla Frontiers in Medicine 2023 - 0 citations - Show abstract - Cite 97.6% topic match

Provides a validated AI model for early sepsis detection. Achieved through integrating a machine learning XGBoost model within EMR systems, enhancing early diagnosis. Model shows high sensitivity and specificity, significantly reducing false positives compared to existing methods.

Provides a validated AI model for early sepsis detection. Achieved through integrating a machine learning XGBoost model within EMR systems, enhancing early diagnosis. Model shows high sensitivity and specificity, significantly reducing false positives compared to existing methods.

97.6%

1.8

2019

[13] DeepAISE - An End-to-End Development and Deployment of a Recurrent Neural Survival Model for Early Prediction of Sepsis S. Shashikumar, ..., and S. Nemati ArXiv 2019 - 9 citations - Show abstract - Cite - PDF 97.6% topic match

Introduces DeepAISE for early sepsis prediction in ICU patients. DeepAISE utilizes a recurrent neural survival model, enhancing early prediction by learning from clinical risk factors. Addresses high false-alarm rates and incorporates into clinical workflows, suggesting practical application and implementation insights.

Introduces DeepAISE for early sepsis prediction in ICU patients. DeepAISE utilizes a recurrent neural survival model, enhancing early prediction by learning from clinical risk factors. Addresses high false-alarm rates and incorporates into clinical workflows, suggesting practical application and implementation insights.

97.6%

0.0

2020

[14] Investigation of Machine Learning Models and Different Feature Sets for the Efficiency of Early Sepsis Prediction from Highly Unbalanced Data Vytautas Abromavičius, ..., and A. Serackis https://doi.org/10.20944/preprints202005.0205.v1 2020 - 0 citations - Show abstract - Cite 97.6% topic match

Investigates efficacy of AI for early sepsis detection in ICU. Explores various machine learning models and data balancing techniques. Utilizes PhysioNet 2019 challenge data, focusing on early prediction from unbalanced datasets.

Investigates efficacy of AI for early sepsis detection in ICU. Explores various machine learning models and data balancing techniques. Utilizes PhysioNet 2019 challenge data, focusing on early prediction from unbalanced datasets.

97.6%

61.2

2019

[15] Early Prediction of Sepsis From Clinical Data: The PhysioNet/Computing in Cardiology Challenge 2019 M. Reyna, ..., and G. Clifford Critical Care Medicine 2019 - 300 citations - Show abstract - Cite 97.6% topic match

Develops algorithms for early sepsis detection in ICU patients. Utilizes large datasets to predict sepsis 6 hours before clinical recognition. Assesses algorithms' effectiveness with a clinical utility-based evaluation metric.

Develops algorithms for early sepsis detection in ICU patients. Utilizes large datasets to predict sepsis 6 hours before clinical recognition. Assesses algorithms' effectiveness with a clinical utility-based evaluation metric.

97.5%

10.9

2021

[16] A Machine Learning Model for Accurate Prediction of Sepsis in ICU Patients Dong Wang, ..., and T. Sun Frontiers in Public Health 2021 - 38 citations - Show abstract - Cite 97.5% topic match

Develops an AI algorithm for early sepsis prediction in ICU patients. Utilizes data from an observational cohort study in an ICU setting. Focuses on reducing sepsis fatalities by predicting sepsis risk early.

Develops an AI algorithm for early sepsis prediction in ICU patients. Utilizes data from an observational cohort study in an ICU setting. Focuses on reducing sepsis fatalities by predicting sepsis risk early.

97.5%

4.0

2020

[17] Early Sepsis Prediction Using Ensemble Learning With Deep Features and Artificial Features Extracted From Clinical Electronic Health Records. Zhengling He, ..., and Z. Fang Critical Care Medicine 2020 - 15 citations - Show abstract - Cite Abstract: OBJECTIVES Sepsis is caused by infection and subsequent overreaction of immune system and will severely threaten human life. The early prediction is important for the treatment of sepsis. This report aims to develop an early prediction method for sepsis 6 hours ahead on the basis of clinical electronic health records. DATA SOURCES Challenge data are released by PhysioNet/Computing in Cardiology Challenge 2019 and obtained from ICU patients in three separate hospital systems. Part of the data from two datasets, including 40,336 subjects, are publicly available, and the remaining are used as hidden test set. A normalized utility score defined by the organizing committee is used for model performance evaluation. STUDY SELECTION The supervised machine learning is applied to tackle this challenge. Specifically, we establish the prediction model under the framework of ensemble learning by integrating the artificial features based on clinical prior knowledge of sepsis with deep features automatically extracted by long short-term memory neural network. DATA EXTRACTION Forty clinical variables, including eight vital signs, 26 laboratory values, and six demographics, were measured and recorded once an hour for each individual, and the binary label (0 or 1) was simultaneously provided for each item. DATA SYNTHESIS The proposed model was evaluated by 30-fold cross-validation. The sensitivity, specificity, and normalized utility score were 0.641 ± 0.022, 0.844 ± 0.007, and 0.401 ± 0.019 on publicly available datasets, respectively. The final normalized utility score our team (UCAS_DataMiner) has obtained was 0.313 on full hidden test set (0.406, 0.373, and -0.215 on test set A, B, and C, respectively). CONCLUSIONS We realized a 6-hour ahead early-onset prediction of sepsis on the basis of clinical electronic health record by ensemble learning. The results indicated the proposed model functioned well in the early prediction of sepsis. In particular, ensemble learning had a significant (p < 0.01) improvement than any single model in performance. 97.5% topic match

Develops an AI model for early sepsis prediction. Utilizes ensemble learning combining deep and artificial features from ICU patient records. Model aims to predict sepsis 6 hours ahead, tested on data from three hospitals.

Develops an AI model for early sepsis prediction. Utilizes ensemble learning combining deep and artificial features from ICU patient records. Model aims to predict sepsis 6 hours ahead, tested on data from three hospitals.

97.5%

1.4

2019

[18] Sepsis Prediction: An Attention-Based Interpretable Approach K. T. Baghaei and S. Rahimi 2019 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) 2019 - 7 citations - Show abstract - Cite 97.5% topic match

Implements an AI attention-based model for sepsis prediction in ICUs. This model reveals factors influencing predictions, enhancing intervention understanding. Focuses on early detection capabilities, aiming to decrease mortality and ICU stays.

Implements an AI attention-based model for sepsis prediction in ICUs. This model reveals factors influencing predictions, enhancing intervention understanding. Focuses on early detection capabilities, aiming to decrease mortality and ICU stays.

97.5%

0.0

2023

[19] AI-based solutions for predicting sepsis in ICUs Charithea Stylianides, ..., and A. Panayides 2023 IEEE EMBS Special Topic Conference on Data Science and Engineering in Healthcare, Medicine and Biology 2023 - 0 citations - Show abstract - Cite 97.5% topic match

Provides insights on an AI-based system for predicting sepsis in ICUs. Utilizes retrospective and prospective ICUs data for early sepsis detection and improving healthcare interventions. Pilots AI system in a real-life setting, emphasizing explainability and ethical AI development in healthcare.

Provides insights on an AI-based system for predicting sepsis in ICUs. Utilizes retrospective and prospective ICUs data for early sepsis detection and improving healthcare interventions. Pilots AI system in a real-life setting, emphasizing explainability and ethical AI development in healthcare.

97.5%

8.4

2019

[20] Sepsis Prediction in Intensive Care Unit Using Ensemble of XGboost Models M. Zabihi, ..., and M. Gabbouj 2019 Computing in Cardiology (CinC) 2019 - 41 citations - Show abstract - Cite 97.5% topic match

Introduces an ensemble of XGboost models for sepsis prediction. Achieved third place in the PhysioNet/Computing in Cardiology Challenge 2019. Specifically evaluates AI effectiveness in early sepsis detection in ICU settings.

Introduces an ensemble of XGboost models for sepsis prediction. Achieved third place in the PhysioNet/Computing in Cardiology Challenge 2019. Specifically evaluates AI effectiveness in early sepsis detection in ICU settings.

97.4%

1.1

2021

[21] Deep Learning Based Sepsis Intervention: The Modelling and Prediction of Severe Sepsis Onset Gavin Tsang and Xianghua Xie 2020 25th International Conference on Pattern Recognition (ICPR) 2021 - 4 citations - Show abstract - Cite 97.4% topic match

Provides a deep learning solution for predicting sepsis onset. Utilizes novel training methodology and functions to predict sepsis up to six hours earlier. Shows significant improvement in prediction accuracy with an F1 score of 0.420.

Provides a deep learning solution for predicting sepsis onset. Utilizes novel training methodology and functions to predict sepsis up to six hours earlier. Shows significant improvement in prediction accuracy with an F1 score of 0.420.

97.4%

2.1

2020

[22] Graph Convolutional Networks-Based Noisy Data Imputation in Electronic Health Record ByeongTak Lee, ..., and Yeha Lee Critical Care Medicine 2020 - 8 citations - Show abstract - Cite 97.4% topic match

Proposes an AI algorithm for early sepsis detection. Utilizes electronic health records from ICU patients to predict sepsis 6 hours before onset. Evaluated using data from over 60,000 ICU patients, showing superior prediction results.

Proposes an AI algorithm for early sepsis detection. Utilizes electronic health records from ICU patients to predict sepsis 6 hours before onset. Evaluated using data from over 60,000 ICU patients, showing superior prediction results.

97.4%

0.5

2020

[23] Multimodal Early Septic Shock Prediction Model using Lasso Regression with Decaying Response Ibrahim Hammoud, ..., and E. Morley 2020 IEEE International Conference on Healthcare Informatics (ICHI) 2020 - 2 citations - Show abstract - Cite 97.4% topic match

Develops an AI model for early septic shock prediction. Utilizes multimodal data achieving 0.89 ROC AUC, predicts 30.64 hours in advance. Compares with existing models, showing improved detection times and accuracy.

Develops an AI model for early septic shock prediction. Utilizes multimodal data achieving 0.89 ROC AUC, predicts 30.64 hours in advance. Compares with existing models, showing improved detection times and accuracy.

97.4%

2.8

2019

[24] Early Prediction of Sepsis Using Multi-Feature Fusion Based XGBoost Learning and Bayesian Optimization Meicheng Yang, ..., and Chengyu Liu 2019 Computing in Cardiology Conference (CinC) 2019 - 13 citations - Show abstract - Cite 97.4% topic match

Develops an AI model for early sepsis prediction in ICU. Utilizes XGBoost learning and Bayesian optimization for feature fusion. Tested on data from 40,336 ICU patients, achieving high accuracy.

Develops an AI model for early sepsis prediction in ICU. Utilizes XGBoost learning and Bayesian optimization for feature fusion. Tested on data from 40,336 ICU patients, achieving high accuracy.

97.4%

5.6

2022

[25] A Machine Learning Model for Early Prediction and Detection of Sepsis in Intensive Care Unit Patients Y. Singh, ..., and R. Singh Journal of Healthcare Engineering 2022 - 13 citations - Show abstract - Cite 97.4% topic match

Provides a machine learning model for early sepsis detection in ICU patients. Models aim to surpass manual scoring and biomarker-based methods in accuracy. Addresses the need for automated solutions to improve timely interventions and reduce mortality.

Provides a machine learning model for early sepsis detection in ICU patients. Models aim to surpass manual scoring and biomarker-based methods in accuracy. Addresses the need for automated solutions to improve timely interventions and reduce mortality.

97.4%

8.8

2020

[26] A Time-Phased Machine Learning Model for Real-Time Prediction of Sepsis in Critical Care Xiang Li, ..., and G. Xie Critical Care Medicine 2020 - 36 citations - Show abstract - Cite Abstract: Supplemental Digital Content is available in the text. Objectives: As a life-threatening condition, sepsis is one of the major public health issues worldwide. Early prediction can improve sepsis outcomes with appropriate interventions. With the PhysioNet/Computing in Cardiology Challenge 2019, we aimed to develop and validate a machine learning algorithm with high prediction performance and clinical interpretability for prediction of sepsis onset during critical care in real-time. Design: Retrospective observational cohort study. Setting: The dataset was collected from three ICUs in three different U.S. hospitals. Two of them were publicly available for model development (offline) and one was used for testing (online). Patients: Forty-thousand three-hundred thirty-six ICU patients from the two model development databases and 24,819 from the test database. There are up to 40 hourly-recorded clinical variables for each ICU stay. The Sepsis-3 criteria were used to confirm sepsis onset. Interventions: None. Measurements and Main Results: Three-hundred twelve features were constructed hourly as the input of our proposed Time-phAsed machine learning model for Sepsis Prediction. Time-phAsed machine learning model for Sepsis Prediction first estimates the likelihood of sepsis onset for each hour of an ICU stay in the following 6 hours, and then makes a binary prediction with three time-phased cutoff values. On the internal validation set, the utility score (official challenge measurement) achieved by Time-phAsed machine learning model for Sepsis Prediction was 0.430. On the test set, the utility score reached was 0.354. Furthermore, Time-phAsed machine learning model for Sepsis Prediction provides an intuitive way to illustrate the impact of the input features on the outcome prediction, which makes it clinically interpretable. Conclusions: The proposed Time-phAsed machine learning model for Sepsis Prediction model is accurate and interpretable for real-time prediction of sepsis onset in critical care, which holds great potential for further evaluation in prospective studies. 97.4% topic match

Develops a machine learning model for real-time sepsis prediction. Utilized data from three U.S. ICUs, focusing on early sepsis detection via 312 features. Model aimed at high prediction performance and clinical interpretability for ICU patients.

Develops a machine learning model for real-time sepsis prediction. Utilized data from three U.S. ICUs, focusing on early sepsis detection via 312 features. Model aimed at high prediction performance and clinical interpretability for ICU patients.

97.3%

20.0

2020

[27] Early Prediction of Sepsis in the ICU Using Machine Learning: A Systematic Review Michael Moor, ..., and K. Borgwardt Frontiers in Medicine 2020 - 78 citations - Show abstract - Cite Abstract: Background: Sepsis is among the leading causes of death in intensive care units (ICUs) worldwide and its recognition, particularly in the early stages of the disease, remains a medical challenge. The advent of an affluence of available digital health data has created a setting in which machine learning can be used for digital biomarker discovery, with the ultimate goal to advance the early recognition of sepsis. Objective: To systematically review and evaluate studies employing machine learning for the prediction of sepsis in the ICU. Data Sources: Using Embase, Google Scholar, PubMed/Medline, Scopus, and Web of Science, we systematically searched the existing literature for machine learning-driven sepsis onset prediction for patients in the ICU. Study Eligibility Criteria: All peer-reviewed articles using machine learning for the prediction of sepsis onset in adult ICU patients were included. Studies focusing on patient populations outside the ICU were excluded. Study Appraisal and Synthesis Methods: A systematic review was performed according to the PRISMA guidelines. Moreover, a quality assessment of all eligible studies was performed. Results: Out of 974 identified articles, 22 and 21 met the criteria to be included in the systematic review and quality assessment, respectively. A multitude of machine learning algorithms were applied to refine the early prediction of sepsis. The quality of the studies ranged from “poor” (satisfying ≤ 40% of the quality criteria) to “very good” (satisfying ≥ 90% of the quality criteria). The majority of the studies (n = 19, 86.4%) employed an offline training scenario combined with a horizon evaluation, while two studies implemented an online scenario (n = 2, 9.1%). The massive inter-study heterogeneity in terms of model development, sepsis definition, prediction time windows, and outcomes precluded a meta-analysis. Last, only two studies provided publicly accessible source code and data sources fostering reproducibility. Limitations: Articles were only eligible for inclusion when employing machine learning algorithms for the prediction of sepsis onset in the ICU. This restriction led to the exclusion of studies focusing on the prediction of septic shock, sepsis-related mortality, and patient populations outside the ICU. Conclusions and Key Findings: A growing number of studies employs machine learning to optimize the early prediction of sepsis through digital biomarker discovery. This review, however, highlights several shortcomings of the current approaches, including low comparability and reproducibility. Finally, we gather recommendations how these challenges can be addressed before deploying these models in prospective analyses. Systematic Review Registration Number: CRD42020200133. 97.3% topic match

Reviews AI models for early sepsis prediction in the ICU. Focuses on machine learning for recognizing sepsis signs earlier in ICU patients. Includes only peer-reviewed articles, excluding studies not set in the ICU.

Reviews AI models for early sepsis prediction in the ICU. Focuses on machine learning for recognizing sepsis signs earlier in ICU patients. Includes only peer-reviewed articles, excluding studies not set in the ICU.

97.3%

2.0

2021

[28] Predicting sepsis in multi-site, multi-national intensive care cohorts using deep learning Michael Moor, ..., and K. Borgwardt ArXiv 2021 - 6 citations - Show abstract - Cite - PDF 97.3% topic match

Develops a deep learning system for predicting sepsis in ICUs. Utilizes data from 156,309 ICU admissions across three countries for validation. Represents the largest multi-national, multi-centre study in ICU sepsis prediction using ML.

Develops a deep learning system for predicting sepsis in ICUs. Utilizes data from 156,309 ICU admissions across three countries for validation. Represents the largest multi-national, multi-centre study in ICU sepsis prediction using ML.

97.3%

3.9

2022

[29] Integrating Physiological Time Series and Clinical Notes with Transformer for Early Prediction of Sepsis Yuqing Wang, ..., and Linda Petzold ArXiv 2022 - 9 citations - Show abstract - Cite - PDF 97.3% topic match

Introduces an AI model for early sepsis prediction in ICU. Utilizes physiological data and clinical notes within first 36 hours of ICU admission. Outperformed six baselines in predictive accuracy, based on MIMIC-III and eICU-CRD datasets.

Introduces an AI model for early sepsis prediction in ICU. Utilizes physiological data and clinical notes within first 36 hours of ICU admission. Outperformed six baselines in predictive accuracy, based on MIMIC-III and eICU-CRD datasets.

97.3%

10.8

2020

[30] An Explainable Artificial Intelligence Predictor for Early Detection of Sepsis Meicheng Yang, ..., and Jianqing Li Critical Care Medicine 2020 - 43 citations - Show abstract - Cite 97.3% topic match

Develops an AI model for early sepsis detection in ICU patients. Utilized electronic health record data from ICU for model development and validation. Focuses on explainable AI, enhancing understanding of prediction decisions.

Develops an AI model for early sepsis detection in ICU patients. Utilized electronic health record data from ICU for model development and validation. Focuses on explainable AI, enhancing understanding of prediction decisions.

97.3%

1.6

2019

[31] A Comparison of Machine Learning Tools for Early Prediction of Sepsis from ICU Data Po-Ya Hsu and Chester Holtz 2019 Computing in Cardiology (CinC) 2019 - 8 citations - Show abstract - Cite 97.3% topic match

Evaluates AI tools for early sepsis prediction in ICU. Compares neural networks, regression, and other algorithms for accuracy. CNN-LSTM showed the highest performance among tested models.

Evaluates AI tools for early sepsis prediction in ICU. Compares neural networks, regression, and other algorithms for accuracy. CNN-LSTM showed the highest performance among tested models.

97.3%

3.9

2019

[32] Automated Prediction of Sepsis Onset Using Gradient Boosted Decision Trees J. Du, ..., and P. Chazal 2019 Computing in Cardiology (CinC) 2019 - 19 citations - Show abstract - Cite 97.3% topic match

Develops an AI model for early sepsis prediction in ICU. Utilizes gradient boosted decision trees based on clinical data. Participated in a challenge, ranking 2nd with notable accuracy.

Develops an AI model for early sepsis prediction in ICU. Utilizes gradient boosted decision trees based on clinical data. Participated in a challenge, ranking 2nd with notable accuracy.

97.3%

0.8

2018

[33] Physiomarkers in Real-Time Physiological Data Streams Predict Adult Sepsis Onset Earlier Than Clinical Practice F. van Wyk, ..., and Rishikesan Kamaleswaran bioRxiv 2018 - 5 citations - Show abstract - Cite 97.3% topic match

Develops AI models for early sepsis detection in ICU patients. Uses physiological data and WBC counts, employing a random forest classifier. Evaluated on a cohort of 1,161 critically ill patients, achieving early prediction.

Develops AI models for early sepsis detection in ICU patients. Uses physiological data and WBC counts, employing a random forest classifier. Evaluated on a cohort of 1,161 critically ill patients, achieving early prediction.

97.3%

0.0

2023

[34] PoEMS: Policy Network-Based Early Warning Monitoring System for Sepsis in Intensive Care Units Hao Dai, ..., and Vincent S. Tseng IEEE Journal of Biomedical and Health Informatics 2023 - 0 citations - Show abstract - Cite 97.3% topic match

Introduces PoEMS for early sepsis detection in ICU patients. PoEMS aims to balance prediction times and accuracy by data analysis. Relevant discussion on addressing early detection challenges and outcomes improvement in sepsis.

Introduces PoEMS for early sepsis detection in ICU patients. PoEMS aims to balance prediction times and accuracy by data analysis. Relevant discussion on addressing early detection challenges and outcomes improvement in sepsis.

97.3%

0.0

2023

[35] Machine Learning framework to predict sepsis disease using stacking ensemble algorithm Laxmi Lydia, ..., and Dr. C. S. S. Anupama Journal Not Provided 2023 - 0 citations - Show abstract - Cite 97.3% topic match

Provides an AI-driven predictive model for early sepsis detection. Utilizes a Stacking Ensemble Meta (SEM) algorithm, enhancing model performance. Model trained on 2019 PhysioNet/Computing in Cardiology data, specifically for ICU patients.

Provides an AI-driven predictive model for early sepsis detection. Utilizes a Stacking Ensemble Meta (SEM) algorithm, enhancing model performance. Model trained on 2019 PhysioNet/Computing in Cardiology data, specifically for ICU patients.

97.3%

0.8

2023

[36] Multi-Subset Approach to Early Sepsis Prediction K. Ewig, ..., and Juhua Hu ArXiv 2023 - 1 citations - Show abstract - Cite - PDF 97.3% topic match

Develops a machine learning algorithm for early sepsis prediction. Predicts sepsis onset 6 hours before clinical suspicion, targeting improved outcomes. Critiques current prediction methods like SOFA for not capturing early prediction effectively.

Develops a machine learning algorithm for early sepsis prediction. Predicts sepsis onset 6 hours before clinical suspicion, targeting improved outcomes. Critiques current prediction methods like SOFA for not capturing early prediction effectively.

97.3%

0.0

2021

[37] SEPRES: Sepsis prediction via a clinical data integration system and real-world studies in the intensive care unit Qiyun Chen, ..., and Huang BEc Journal Not Provided 2021 - 0 citations - Show abstract - Cite 97.3% topic match

Provides AI-driven sepsis prediction assessments in ICU. Shows high accuracy (AUC scores) in predicting sepsis up to 5 hours early. Discusses real-world implementation and the challenges of false predictions in a clinical setting.

Provides AI-driven sepsis prediction assessments in ICU. Shows high accuracy (AUC scores) in predicting sepsis up to 5 hours early. Discusses real-world implementation and the challenges of false predictions in a clinical setting.

97.3%

1.4

2022

[38] Early Prediction of Sepsis for ICU Patients using Gradient Boosted Tree Teh Xuan Ying and Asma’ Abu-Samah 2022 IEEE International Conference on Automatic Control and Intelligent Systems (I2CACIS) 2022 - 3 citations - Show abstract - Cite 97.3% topic match

Provides evaluation of AI models for early sepsis prediction in ICU patients. Utilizes Gradient Boosted Tree among others, aiming for 15 hours before sepsis onset prediction. Tested on MIMIC-III database, highlighting a focus on machine learning algorithms like Decision Tree and Random Forest.

Provides evaluation of AI models for early sepsis prediction in ICU patients. Utilizes Gradient Boosted Tree among others, aiming for 15 hours before sepsis onset prediction. Tested on MIMIC-III database, highlighting a focus on machine learning algorithms like Decision Tree and Random Forest.

97.3%

0.0

2022

[39] A 43.6 TOPS/W AI Classifier with Sensor Fusion for Sepsis Onset Prediction Sudarsan Sadasivuni, ..., and A. Sanyal 2022 IEEE Biomedical Circuits and Systems Conference (BioCAS) 2022 - 0 citations - Show abstract - Cite 97.3% topic match

Introduces an AI framework for predicting sepsis onset. Achieves early detection via ECG and medical record data integration. Demonstrates high accuracy (92.9%) and efficiency in a clinical dataset from MIMIC–III.

Introduces an AI framework for predicting sepsis onset. Achieves early detection via ECG and medical record data integration. Demonstrates high accuracy (92.9%) and efficiency in a clinical dataset from MIMIC–III.

97.2%

1.0

2021

[40] On the early detection of Sepsis in MIMIC-III M. Medina and P. Sala 2021 IEEE 9th International Conference on Healthcare Informatics (ICHI) 2021 - 3 citations - Show abstract - Cite 97.2% topic match

Introduces an AI model for early sepsis detection in ICU. Uses machine learning with conformal prediction on MIMIC-III data for prediction shortly after ICU admission. Focuses on improving diagnosis timing and accuracy, critical in ICU patient care.

Introduces an AI model for early sepsis detection in ICU. Uses machine learning with conformal prediction on MIMIC-III data for prediction shortly after ICU admission. Focuses on improving diagnosis timing and accuracy, critical in ICU patient care.

97.2%

6.5

2021

[41] A novel artificial intelligence based intensive care unit monitoring system: using physiological waveforms to identify sepsis Maximiliano Mollura, ..., and R. Barbieri Philosophical Transactions of the Royal Society A 2021 - 18 citations - Show abstract - Cite 97.2% topic match

Introduces an AI system for early sepsis detection in ICU. Utilizes physiological waveforms and a cardiovascular model for prediction. Achieved high benchmark results, suggesting effectiveness in early sepsis identification.

Introduces an AI system for early sepsis detection in ICU. Utilizes physiological waveforms and a cardiovascular model for prediction. Achieved high benchmark results, suggesting effectiveness in early sepsis identification.

97.2%

1.5

2020

[42] AIDEx - An Open-source Platform for Real-Time Forecasting Sepsis and A Case Study on Taking ML Algorithms to Production Fatemeh Amrollahi, ..., and S. Nemati 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) 2020 - 6 citations - Show abstract - Cite 97.2% topic match

Introduces AIDEx for early sepsis detection via ML. Predicts sepsis 4-6 hours before clinical recognition, improving early treatment. AIDEx is an open-source, EHR vendor-agnostic platform for real-time patient monitoring.

Introduces AIDEx for early sepsis detection via ML. Predicts sepsis 4-6 hours before clinical recognition, improving early treatment. AIDEx is an open-source, EHR vendor-agnostic platform for real-time patient monitoring.

97.2%

0.8

2019

[43] Time-Specific Metalearners for the Early Prediction of Sepsis M. Vollmer, ..., and S. Kuhn 2019 Computing in Cardiology (CinC) 2019 - 4 citations - Show abstract - Cite 97.2% topic match

Provides evaluation of AI models for early sepsis prediction in ICU. Uses time-specific ensembles and XGBoost for 6-hour prior prediction, trained on ICU stay data. Performance measured by utility scores; highlights variable importance in prediction.

Provides evaluation of AI models for early sepsis prediction in ICU. Uses time-specific ensembles and XGBoost for 6-hour prior prediction, trained on ICU stay data. Performance measured by utility scores; highlights variable importance in prediction.

97.2%

0.0

2020

[44] Accuracy Prediction and Classification using Machine Learning Techniques for Sepsis Dr. R. K. Kavitha, ..., and Ms. S. Harini Journal Not Provided 2020 - 0 citations - Show abstract - Cite 97.2% topic match

Develops an AI-based prediction system for early sepsis detection. Utilizes neural network algorithms with clinical ICU data for prediction. Aims to reduce hospital mortality by predicting sepsis onset earlier.

Develops an AI-based prediction system for early sepsis detection. Utilizes neural network algorithms with clinical ICU data for prediction. Aims to reduce hospital mortality by predicting sepsis onset earlier.

97.2%

0.0

2018

[45] 1500: SEPSIS PREDICTION USING BIG DATA ANALYTICS-BASED TOOLS Itai M. Pessach, ..., and V. Herasevich Critical Care Medicine 2018 - 0 citations - Show abstract - Cite Abstract: www.ccmjournal.org Critical Care Medicine • Volume 46 • Number 1 (Supplement) Learning Objectives: In recent years, a wide variety of efforts have focused on the prediction and recognition of sepsis. These include computerized rule-based surveillance algorithms and alert tools. However, a clinically relevant application of such tools is often restricted by factors such as suboptimal sensitivity and specificity which have caused implementation barriers. In the present study, we tested the diagnostic performance of a recently developed realtime sepsis prediction model using Big Data techniques to detect Sepsis in ICU patients. Methods: The study cohort is 1088 consecutive adult patient-stays at a medical ICU in a tertiary academic medical center in Rochester, MN during the 6 months period between September 2016 and February 2017. The sepsis detection model was developed by Intensix (Netanya, Israel) using Big Data analytics tools on a large group of critically ill patients in several tertiary centers. The model utilizes over 600 variables per patient that are acquired in real time from the EMR. We conducted a prospective observational diagnostic performance study comparing the Intensix sepsis model to a clinical expert case by case review (two trained reviewers with a third expert reviewer for cases of disagreement) as the gold standard. Sensitivity, specificity and other diagnostic performance statistics were calculated. Results: During the study period, 275 patients had sepsis events that were tagged by the reviewers. The tested model showed sensitivity of 0.855 and a specificity of 0.809 for detection of sepsis, with a PPV of 0.603 and an NPV of 0.943. The Intensix sepsis model generated 155 false positive alerts for patients that were deemed not to have sepsis by the clinical team. Interestingly, 26 of these patients (17%) had other life-threatening events including massive GI bleeding, arrhythmia, cardiac arrest etc. The model and system showed high reliability with no down time and the ability to process the large volumes of data needed for the execution of the algorithm. Conclusions: The development of a model for the detection of sepsis in patients admitted to the ICU with high diagnostic performance. 97.2% topic match

Evaluates a real-time AI sepsis prediction model in ICU patients. Utilizes Big Data analytics with over 600 variables per patient from EMR. Prospective study, compared AI model against clinical expert review.

Evaluates a real-time AI sepsis prediction model in ICU patients. Utilizes Big Data analytics with over 600 variables per patient from EMR. Prospective study, compared AI model against clinical expert review.

97.2%

0.7

2021

[46] Early Sepsis Detection using Machine Learning and Neural Networks N. Shah, ..., and Pankaj Sonawane 2021 2nd Global Conference for Advancement in Technology (GCAT) 2021 - 2 citations - Show abstract - Cite 97.2% topic match

Proposes AI models for predicting sepsis 6 hours early. Utilizes machine learning and neural networks tested on the MIMIC3 dataset. Compares several AI methods, emphasizing early diagnosis in ICU settings.

Proposes AI models for predicting sepsis 6 hours early. Utilizes machine learning and neural networks tested on the MIMIC3 dataset. Compares several AI methods, emphasizing early diagnosis in ICU settings.

97.2%

0.0

2023

[47] Comparing artificial intelligence strategies for early sepsis detection in the ICU: an experimental study Javier Solís-García, ..., and Isabel A. Nepomuceno-Chamorro Applied Intelligence 2023 - 0 citations - Show abstract - Cite 97.2% topic match

97.1%

0.0

2023

[48] Predicting the Onset of Sepsis Using Vital Signs Data: A Machine Learning Approach Antuan V. Tran, ..., and Anthony Shao Clinical Nursing Research 2023 - 0 citations - Show abstract - Cite 97.1% topic match

Provides an AI-driven predictive model for early sepsis detection. Utilizes vital signs data from ICU patients to predict sepsis onset. Demonstrates superior performance over traditional scoring systems in a large dataset.

Provides an AI-driven predictive model for early sepsis detection. Utilizes vital signs data from ICU patients to predict sepsis onset. Demonstrates superior performance over traditional scoring systems in a large dataset.

97.1%

0.0

2022

[49] SEPRES: Intensive Care Unit Clinical Data Integration System to Predict Sepsis Qiyu Chen, ..., and Lei Li Applied Clinical Informatics 2022 - 0 citations - Show abstract - Cite 97.1% topic match

Develops SEPRES, an ICU sepsis prediction system. Integrates ICU clinical data to predict sepsis 5 hours early. Deployed in Ruijin Hospital, confirms system's feasibility.

Develops SEPRES, an ICU sepsis prediction system. Integrates ICU clinical data to predict sepsis 5 hours early. Deployed in Ruijin Hospital, confirms system's feasibility.

97.1%

0.3

2021

[50] Early prediction and monitoring of sepsis using sequential long short term memory model D. Sharma, ..., and Shikha Brahmachari Expert Systems 2021 - 1 citations - Show abstract - Cite 97.1% topic match

Provides an LSTM-based AI model for early sepsis prediction in ICU. Model uses time series data from IoT devices for real-time monitoring. Focuses specifically on sepsis prediction using historical medical data.

Provides an LSTM-based AI model for early sepsis prediction in ICU. Model uses time series data from IoT devices for real-time monitoring. Focuses specifically on sepsis prediction using historical medical data.

97.1%

1.3

2023

[51] Artificial intelligence can use physiological parameters to optimize treatment strategies and predict clinical deterioration of sepsis in ICU Quan Zhang, ..., and Wenjia Zhang Physiological Measurement 2023 - 2 citations - Show abstract - Cite 97.1% topic match

Designs an AI-driven system for early sepsis prediction in ICUs. Utilizes deep reinforcement learning on physiological data for treatment strategy and risk prediction. Demonstrates reduced mortality through AI-enhanced treatment recommendations in sepsis management.

Designs an AI-driven system for early sepsis prediction in ICUs. Utilizes deep reinforcement learning on physiological data for treatment strategy and risk prediction. Demonstrates reduced mortality through AI-enhanced treatment recommendations in sepsis management.

97.1%

0.2

2019

[52] An Ensemble LSTM Architecture for Clinical Sepsis Detection S. Schellenberger, ..., and A. Koelpin 2019 Computing in Cardiology (CinC) 2019 - 1 citations - Show abstract - Cite 97.1% topic match

Implements LSTM for early sepsis detection in ICU. Targets automatic detection of sepsis six hours before traditional methods. Utilizes hourly physiological data, achieving an utility score of 0.29.

Implements LSTM for early sepsis detection in ICU. Targets automatic detection of sepsis six hours before traditional methods. Utilizes hourly physiological data, achieving an utility score of 0.29.

97.1%

0.0

2024

[53] Advancing Early Detection of Sepsis With Temporal Convolutional Networks Using ECG Signals Merve Apalak and K. Kiasaleh IEEE Access 2024 - 0 citations - Show abstract - Cite Abstract: In the hours leading up to the onset time of sepsis, the autonomic nervous system presents sub-clinical indicators of disease that may not be observable to providers. The objective of this research is to create an interpretable sepsis prediction algorithm utilizing continuous electrocardiography (ECG) signals, with the aim of implementing it in patient monitoring systems for individuals in intensive care units (ICU). We develop an early sepsis detection algorithm utilizing two datasets; in particular, the Medical Information Mart for Intensive Care (MIMIC-III) Clinical Dataset and MIMIC-Waveform Database. We carry out a systematic approach to selecting ECG segments of superior quality that are recorded in highly dynamic intensive care unit environments. Later, we use the single-lead ECG waveform to investigate the potential of heart rate variability (HRV) for continuous monitoring. In this study, 715 patients were included, of whom 65 are sepsis patients labeled with recent sepsis definition on an hourly basis. The predictive potential of the critical features is visualized to assist the interpretation of the model in a clinical practice. Moreover, since we are framing the early sepsis prediction as a supervised time series classification task, we evaluate the model performance by implementing Temporal Convolutional Networks (TCN). Performance analysis reported with varying prediction windows preceding sepsis onset time using area under the receiver-operating-characteristic curve (AUROC) and area under the precision-recall curve (AUPRC). The deep learning model delivers promising results by leveraging time series with the use of temporal convolutions. Our findings reveal that the HRV characteristics of adults can be a valuable indicator for continuous sepsis monitoring in an ICU. Finally, this research work adds to the field of early sepsis detection by providing an annotated continuous waveform dataset from the MIMIC-Waveform Database, which is made accessible to the public. 97.1% topic match

Develops an AI algorithm for early sepsis detection using ECG. Utilizes the MIMIC-III Clinical Dataset and waveform data for model training. Focuses on ICU patients, aiming to improve timely interventions and outcomes.

Develops an AI algorithm for early sepsis detection using ECG. Utilizes the MIMIC-III Clinical Dataset and waveform data for model training. Focuses on ICU patients, aiming to improve timely interventions and outcomes.

97.1%

0.0

2019

[54] Gradient Boosting Machine for Early Prediction of Sepsis Using Clinical Data S. Chami and K. Tavakolian Journal Not Provided 2019 - 0 citations - Show abstract - Cite 97.1% topic match

Introduces an AI model for early sepsis detection using clinical data. Utilizes gradient boosting machines for improved sepsis risk monitoring in ICU settings. Achieved significant results, including a high area under the ROC curve, indicating effective predictive capability.

Introduces an AI model for early sepsis detection using clinical data. Utilizes gradient boosting machines for improved sepsis risk monitoring in ICU settings. Achieved significant results, including a high area under the ROC curve, indicating effective predictive capability.

97.1%

0.0

2024

[55] Early prediction of onset of sepsis in Clinical Setting Fahim Mohammad, ..., and P. Mirhaji ArXiv 2024 - 0 citations - Show abstract - Cite - PDF 97.1% topic match

Provides an AI model for early sepsis prediction in ICU. Utilizes XGBoost on clinical data with evaluation using normalized utility score. Achieved promising results in both test and prospective data sets.

Provides an AI model for early sepsis prediction in ICU. Utilizes XGBoost on clinical data with evaluation using normalized utility score. Achieved promising results in both test and prospective data sets.

97.1%

7.1

2020

[56] Temporal Differential Expression of Physiomarkers Predicts Sepsis in Critically Ill Adults Akram Mohammed, ..., and Rishikesan Kamaleswaran SHOCK 2020 - 27 citations - Show abstract - Cite 97.1% topic match

Develops AI for early sepsis prediction in ICU patients. Utilized streaming physiological data from 29,552 adult ICU admissions. Study conducted across five regional hospitals over 18 months.

Develops AI for early sepsis prediction in ICU patients. Utilized streaming physiological data from 29,552 adult ICU admissions. Study conducted across five regional hospitals over 18 months.

97.1%

0.9

2023

[57] Temporal convolution attention model for sepsis clinical assistant diagnosis prediction. Yong Li and Yang Wang Mathematical biosciences and engineering : MBE 2023 - 1 citations - Show abstract - Cite 97.1% topic match

Develops the TCASP model for early sepsis detection in ICU. Utilizes ICU electronic medical records to identify high-risk sepsis patients. Aims at reducing mortality through smart surveillance and early warning.

Develops the TCASP model for early sepsis detection in ICU. Utilizes ICU electronic medical records to identify high-risk sepsis patients. Aims at reducing mortality through smart surveillance and early warning.

97.1%

1.1

2021

[58] Early Prediction of Sepsis using Machine Learning Anuraag Shankar, ..., and Tanusri Bhowmick 2021 11th International Conference on Cloud Computing, Data Science & Engineering (Confluence) 2021 - 4 citations - Show abstract - Cite 97.1% topic match

Develops a machine learning classifier for early sepsis prediction. Utilizes EMR, vital signs, and demographics to predict sepsis up to six hours before clinical diagnosis. Investigates six models, including Random Forest and Neural Network, emphasizing interpretability and unprecedented evaluation metrics.

Develops a machine learning classifier for early sepsis prediction. Utilizes EMR, vital signs, and demographics to predict sepsis up to six hours before clinical diagnosis. Investigates six models, including Random Forest and Neural Network, emphasizing interpretability and unprecedented evaluation metrics.

97.1%

1.3

2021

[59] Improving Early Sepsis Prediction with Multi Modal Learning Fred Qin, ..., and Taha A. Kass-Hout ArXiv 2021 - 4 citations - Show abstract - Cite - PDF 97.1% topic match

Introduces a multi-modal AI model for early sepsis prediction. Utilizes both structured data and clinical text, enhancing prediction via NLP technologies like BERT. Demonstrates superior performance on ICU data, outperforming existing clinical criteria.

Introduces a multi-modal AI model for early sepsis prediction. Utilizes both structured data and clinical text, enhancing prediction via NLP technologies like BERT. Demonstrates superior performance on ICU data, outperforming existing clinical criteria.

97.0%

6.2

2021

[60] Multi-Branching Temporal Convolutional Network for Sepsis Prediction Zekai Wang and B. Yao IEEE Journal of Biomedical and Health Informatics 2021 - 19 citations - Show abstract - Cite 97.0% topic match

Introduces MB-TCN for early sepsis prediction in ICU. Demonstrates handling of complex ICU data, improving prediction accuracy. Evaluated using real data from the PhysioNet Challenge, outperforming common methods.

Introduces MB-TCN for early sepsis prediction in ICU. Demonstrates handling of complex ICU data, improving prediction accuracy. Evaluated using real data from the PhysioNet Challenge, outperforming common methods.

97.0%

3.0

2020

[61] Two-Step Imputation and AdaBoost-Based Classification for Early Prediction of Sepsis on Imbalanced Clinical Data A. Baniasadi, ..., and M. Ghassemi Critical Care Medicine 2020 - 11 citations - Show abstract - Cite 97.0% topic match

Provides a machine learning approach for early sepsis prediction. Implements a two-step imputation and AdaBoost classification to predict sepsis 6 hours before clinical diagnosis. Utilizes clinical data from over 40,000 patients across three U.S. hospitals, focusing on ICU settings.

Provides a machine learning approach for early sepsis prediction. Implements a two-step imputation and AdaBoost classification to predict sepsis 6 hours before clinical diagnosis. Utilizes clinical data from over 40,000 patients across three U.S. hospitals, focusing on ICU settings.

97.0%

1.2

2022

[62] A Comprehensive Machine Learning Based Pipeline for an Accurate Early Prediction of Sepsis in ICU B. C. Srimedha, ..., and V. Mayya IEEE Access 2022 - 3 citations - Show abstract - Cite Abstract: Sepsis is a lethal infection-related illness that has an extremely high fatality rate, especially among intensive care unit patients. Early and precise recognition of sepsis is critical as delayed treatment increases the mortality rate dramatically. System inflammatory response syndrome, quick sequential organ failure assessment, and modified early warning score are the traditional clinical score systems in practice to detect sepsis. But the scoring systems fail in the early prediction of sepsis, a stage in which if a patient is treated immediately, the mortality rate will reduce significantly. The proposed classifier can accurately predict sepsis up to six hours before the disease is clinically diagnosed. The patient’s electronic medical records, demographics, and vital signs are used to achieve this. The study uses data set adaptive data preprocessing strategies. The proposed method adds value to existing literature by introducing a novel outlier-based mean-median data imputation technique that enhances the prediction’s overall accuracy. The primary factors that influence the classifier’s predictions have been outlined, making the model easier to understand for medical professionals. For the classification of patients as sepsis positive or negative, four algorithms were investigated: Random Forest, Logistic Regression, Gradient Boosting, and Decision Tree. Of all the prediction algorithms, Random Forest gives the best results with an accuracy of 99.01%, F1-score of 99%, and an area under the receiver operator characteristic curve of 99.99%. Even for a 24-hour early prediction of sepsis, the random forest method is proven to provide greater prediction accuracy while logistic regression provides the least prediction accuracy. We attribute this to the fact that, unlike regression models, random forests do not require that the model have a linear relationship between the dependent and independent variables. The evaluation measures produced are useful and can be tremendously valuable in predicting sepsis in a timely and accurate manner. 97.0% topic match

Develops AI classifier for early sepsis prediction in ICU. Predicts sepsis up to six hours before clinical diagnosis using patient data. Enhances prediction accuracy with novel data imputation technique.

Develops AI classifier for early sepsis prediction in ICU. Predicts sepsis up to six hours before clinical diagnosis using patient data. Enhances prediction accuracy with novel data imputation technique.

97.0%

3.1

2022

[63] Dynamic Sepsis Prediction for Intensive Care Unit Patients Using XGBoost-Based Model With Novel Time-Dependent Features Shuhui Liu, ..., and Xin Sun IEEE Journal of Biomedical and Health Informatics 2022 - 7 citations - Show abstract - Cite 97.0% topic match

Introduces an AI-based XGBoost model for sepsis prediction. Utilizes dynamic, time-dependent data from ICU patient records. Demonstrates improved prediction accuracy, with a significant increase in AUROC.

Introduces an AI-based XGBoost model for sepsis prediction. Utilizes dynamic, time-dependent data from ICU patient records. Demonstrates improved prediction accuracy, with a significant increase in AUROC.

97.0%

2.7

2019

[64] A Multi-Task Imputation and Classification Neural Architecture for Early Prediction of Sepsis from Multivariate Clinical Time Series Yale Chang, ..., and S. Parvaneh 2019 Computing in Cardiology (CinC) 2019 - 13 citations - Show abstract - Cite 97.0% topic match

Develops an AI model for early sepsis prediction in ICU. Uses multivariate clinical time series and patient demographics for prediction. Focuses on predicting sepsis onset six hours earlier than usual methods.

Develops an AI model for early sepsis prediction in ICU. Uses multivariate clinical time series and patient demographics for prediction. Focuses on predicting sepsis onset six hours earlier than usual methods.

96.9%

1.2

2019

[65] Utilizing Informative Missingness for Early Prediction of Sepsis Janmajay Singh, ..., and N. Kato 2019 Computing in Cardiology (CinC) 2019 - 6 citations - Show abstract - Cite 96.9% topic match

Provides an AI model for early sepsis prediction in ICU. Utilizes XGBoost and informative missingness of data for prediction. Model shifts sepsis labels to 3 hours pre-optimal for early detection.

Provides an AI model for early sepsis prediction in ICU. Utilizes XGBoost and informative missingness of data for prediction. Model shifts sepsis labels to 3 hours pre-optimal for early detection.

96.9%

0.0

2023

[66] A Machine Learning Model Integrated with the Clinical Workflow Detects Sepsis Early with High Sensitivity and Specificity M. Mahyoub, ..., and A. Shukla medRxiv 2023 - 0 citations - Show abstract - Cite 96.9% topic match

Provides evaluation of an AI model for early sepsis detection. Achieved high sensitivity and specificity using XGBoost and Shapely values. Integrated successfully with an existing Electronic Medical Record system.

Provides evaluation of an AI model for early sepsis detection. Achieved high sensitivity and specificity using XGBoost and Shapely values. Integrated successfully with an existing Electronic Medical Record system.

96.9%

0.0

2020

[67] Comparison Of Three Artificial Intelligence Algorithms For Sepsis Prediction J. Musulin, ..., and Z. Car World health 2020 - 0 citations - Show abstract - Cite 96.9% topic match

Compares AI algorithms for sepsis prediction effectiveness. Evaluated SVM, KNN, and ANN using 2277 data points from ICU patients. Found ANN to be most effective, achieving an AUC of 0.992.

Compares AI algorithms for sepsis prediction effectiveness. Evaluated SVM, KNN, and ANN using 2277 data points from ICU patients. Found ANN to be most effective, achieving an AUC of 0.992.

96.9%

1.6

2019

[68] TASP: A Time-Phased Model for Sepsis Prediction Xiang Li, ..., and G. Xie 2019 Computing in Cardiology (CinC) 2019 - 8 citations - Show abstract - Cite 96.9% topic match

Introduces TASP for early sepsis prediction in ICU patients. TASP uses a time-phased AI model improving prediction accuracy at different ICU stages. Evaluation with 10-fold cross-validation achieved a score of 0.415.

Introduces TASP for early sepsis prediction in ICU patients. TASP uses a time-phased AI model improving prediction accuracy at different ICU stages. Evaluation with 10-fold cross-validation achieved a score of 0.415.

96.9%

0.8

2022

[69] Using Machine Learning Algorithms to predict sepsis and its stages in ICU patients Nimrah Ghias, ..., and Mehak Rafiq medRxiv 2022 - 2 citations - Show abstract - Cite 96.9% topic match

Evaluates ML models for early sepsis prediction in ICU patients. Xgboost model outperforms others with high accuracy and precision. Focused on predicting sepsis at ICU admission using vital signs.

Evaluates ML models for early sepsis prediction in ICU patients. Xgboost model outperforms others with high accuracy and precision. Focused on predicting sepsis at ICU admission using vital signs.

96.9%

2.7

2022

[70] Machine Learning Models for Early Prediction of Sepsis on Large Healthcare Datasets J. E. Camacho-Cogollo, ..., and E. Iadanza Electronics 2022 - 6 citations - Show abstract - Cite 96.9% topic match

Provides experimental study on AI models for early sepsis prediction. Utilizes vital signs, lab test results, and demographics in MIMIC-III dataset. AI models outperform traditional SOFA and qSOFA scores at predicting sepsis onset.

Provides experimental study on AI models for early sepsis prediction. Utilizes vital signs, lab test results, and demographics in MIMIC-III dataset. AI models outperform traditional SOFA and qSOFA scores at predicting sepsis onset.

96.9%

0.0

2022

[71] Performance Analysis of Class Imbalance Handling Techniques for Early Sepsis Prediction using Machine Learning Algorithms Aparna R. Shenoy and B. K 2022 8th International Conference on Smart Structures and Systems (ICSSS) 2022 - 0 citations - Show abstract - Cite 96.9% topic match

Develops an AI model for early sepsis prediction in ICU patients. Examines class imbalance techniques to enhance ML model performance. Demonstrates high accuracy, precision, recall, and AUROC with SPMPH model.

Develops an AI model for early sepsis prediction in ICU patients. Examines class imbalance techniques to enhance ML model performance. Demonstrates high accuracy, precision, recall, and AUROC with SPMPH model.

96.9%

0.5

2022

[72] SEPRES: Sepsis prediction via the clinical data integration system in the ICU Q. Chen, ..., and L. Li medRxiv 2022 - 1 citations - Show abstract - Cite 96.9% topic match

Introduces SEPRES, an AI-driven sepsis prediction system in ICU. SEPRES integrates multiple data sources for real-time sepsis early warning. Deployment at Ruijin Hospital confirmed the system's effectiveness in early sepsis detection.

Introduces SEPRES, an AI-driven sepsis prediction system in ICU. SEPRES integrates multiple data sources for real-time sepsis early warning. Deployment at Ruijin Hospital confirmed the system's effectiveness in early sepsis detection.

96.9%

8.4

2019

[73] Early Recognition of Sepsis with Gaussian Process Temporal Convolutional Networks and Dynamic Time Warping Michael Moor, ..., and K. Borgwardt Machine Learning in Health Care 2019 - 46 citations - Show abstract - Cite 96.9% topic match

Introduces AI models for early sepsis detection in ICU. Uses deep learning and time-series analysis for predicting sepsis onset. Focuses on handling irregularly-spaced ICU data, improving prediction accuracy.

Introduces AI models for early sepsis detection in ICU. Uses deep learning and time-series analysis for predicting sepsis onset. Focuses on handling irregularly-spaced ICU data, improving prediction accuracy.

96.9%

2.1

2018

[74] Sepsis Prediction and Vital Signs Ranking in Intensive Care Unit Patients Avijit Mitra and Khalid Ashraf ArXiv 2018 - 12 citations - Show abstract - Cite - PDF 96.9% topic match

Provides evaluation of AI models for early sepsis detection. Utilizes neural networks and ML on ICU patient data, improving AUC scores. Compares ensemble and single-model performance using vital signs in sepsis prediction.

Provides evaluation of AI models for early sepsis detection. Utilizes neural networks and ML on ICU patient data, improving AUC scores. Compares ensemble and single-model performance using vital signs in sepsis prediction.

96.9%

0.6

2018

[75] Evaluating a sepsis prediction machine learning algorithm in the emergency department and intensive care unit: a before and after comparative study Hoyt J Burdick, ..., and R. Das Journal Not Provided 2018 - 4 citations - Show abstract - Cite 96.9% topic match

Evaluates AI-driven predictive model for sepsis in ICU. Compares machine learning algorithm to traditional detection system in a clinical study. Study conducted in both emergency department and ICU settings; focuses on prediction effectiveness.

Evaluates AI-driven predictive model for sepsis in ICU. Compares machine learning algorithm to traditional detection system in a clinical study. Study conducted in both emergency department and ICU settings; focuses on prediction effectiveness.

96.8%

1.0

2021

[76] An Explainable Machine Learning Model for Early Prediction of Sepsis Using ICU Data Naimahmed Nesaragi and Shivnarayan Patidar Infectious Diseases and Sepsis [Working Title] 2021 - 3 citations - Show abstract - Cite Abstract: Early identification of individuals with sepsis is very useful in assisting clinical triage and decision-making, resulting in early intervention and improved outcomes. This study aims to develop an explainable machine learning model with the clinical interpretability to predict sepsis onset before 6 hours and validate with improved prediction risk power for every time interval since admission to the ICU. The retrospective observational cohort study is carried out using PhysioNet Challenge 2019 ICU data from three distinct hospital systems, viz. A, B, and C. Data from A and B were shared publicly for training and validation while sequestered data from all three cohorts were used for scoring. However, this study is limited only to publicly available training data. Training data contains 15,52,210 patient records of 40,336 ICU patients with up to 40 clinical variables (sourced for each hour of their ICU stay) divided into two datasets, based on hospital systems A and B. The clinical feature exploration and interpretation for early prediction of sepsis is achieved using the proposed framework, viz. the explainable Machine Learning model for Early Prediction of Sepsis (xMLEPS). A total of 85 features comprising the given 40 clinical variables augmented with 10 derived physiological features and 35 time-lag difference features are fed to xMLEPS for the said prediction task of sepsis onset. A ten-fold cross-validation scheme is employed wherein an optimal prediction risk threshold is searched for each of the 10 LightGBM models. These optimum threshold values are later used by the corresponding models to refine the predictive power in terms of utility score for the prediction of labels in each fold. The entire framework is designed via Bayesian optimization and trained with the resultant feature set of 85 features, yielding an average normalized utility score of 0.4214 and area under receiver operating characteristic curve of 0.8591 on publicly available training data. This study establish a practical and explainable sepsis onset prediction model for ICU data using applied ML approach, mainly gradient boosting. The study highlights the clinical significance of physiological inter-relations among the given and proposed clinical signs via feature importance and SHapley Additive exPlanations (SHAP) plots for visualized interpretation. 96.8% topic match

Develops an AI model for early sepsis prediction in ICU. Utilizes ICU data for explainable machine learning, aiming for prediction before 6 hours. Relies on PhysioNet 2019 data, involves retrospective study from multiple hospitals.

Develops an AI model for early sepsis prediction in ICU. Utilizes ICU data for explainable machine learning, aiming for prediction before 6 hours. Relies on PhysioNet 2019 data, involves retrospective study from multiple hospitals.

96.8%

1.6

2022

[77] Improving Sepsis Prediction Performance Using Conditional Recurrent Adversarial Networks Merve Apalak and K. Kiasaleh IEEE Access 2022 - 4 citations - Show abstract - Cite 96.8% topic match

Introduces a novel AI model for early sepsis prediction in ICUs. Utilizes Conditional GANs and LSTM networks to address missing data issues. Focuses on improving detection accuracy by reconstructing incomplete patient datasets.

Introduces a novel AI model for early sepsis prediction in ICUs. Utilizes Conditional GANs and LSTM networks to address missing data issues. Focuses on improving detection accuracy by reconstructing incomplete patient datasets.

96.8%

1.3

2023

[78] AI-Enabled Solutions, Explainability and Ethical Concerns for Predicting Sepsis in ICUs: A Systematic Review Christina-Athanasia I. Alexandropoulou, ..., and A. Panayides 2023 IEEE 19th International Conference on e-Science (e-Science) 2023 - 1 citations - Show abstract - Cite 96.8% topic match

Provides a systematic review on AI for early sepsis prediction in ICUs. Identifies knowledge gaps and discusses explainability, ethical concerns in AI-driven sepsis prediction. Conducts a literature search focusing on articles published within the last five years.

Provides a systematic review on AI for early sepsis prediction in ICUs. Identifies knowledge gaps and discusses explainability, ethical concerns in AI-driven sepsis prediction. Conducts a literature search focusing on articles published within the last five years.

96.8%

0.0

2019

[79] Modelo de predicción de sepsis a partir de datos históricos de pacientes en una unidad de cuidados intensivos Zuleimi Esteffanny González Muñoz and Pablo Merizalde Maya Journal Not Provided 2019 - 0 citations - Show abstract - Cite Abstract: The growing availability of data and the fast development of data analysis methods, have made possible the recent successful applications of Artificial Intelligence in health. The use of these technological advances, allow us to help in the different processes of health institutions such as in the prediction and diagnosis of diseases. Among these, sepsis is considered a condition with a high mortality rate, especially in intensive care units. This condition, can become very serious due to the different ways of manifesting, which makes it difficult to diagnose. The verification of some general inflammatory variables, allows us to indicate the lethality of the infection. Currently, the most common is the use of indicators such as SOFA, qSOFA and SAPS-II to predict the possibility of sepsis, because it is closely related to mortality. Although, in developed countries are already using methods based on historical data with artificial intelligence algorithms to make an early prediction. In the present work we analyzed the data stored in the free database MIMIC-III, which contains information of patients admitted to the intensive care unit of The Beth Israel Deaconess Medical Center in Boston, Massachusetts. A series of clinical variables of the patients were used, which were passed through hard rules that generate a numerical value or probability that is related to the severity of the condition. The chosen variables, correspond to those used in the mentioned indicators in order to predict the existence or not of sepsis and the mortality of patients. Therefore, the objective of the work is to perform an early prediction model of sepsis, using artificial intelligence methods and to compare it with the different indicators for the diagnosis of this condition. The procedure carried out was based on the CRISP-DM methodology, where the data was obtained, an analysis of their quality was done, the variables of the aforementioned indicators were selected, a cleaning of the data was performed, and a single view was obtained which was used to train selected supervised classifiers: decision tree, KNN, naive bayes, neural network and support vector machines. For this classification, the data were first divided into learning and validation data, the models were implemented, and finally the results were corroborated, choosing the best models and comparing the algorithms among themselves, through the evaluation of metrics using cross-validation. The results indicated that the models of machine learning and deep learning implemented, are able to equal and even improve the predictions of hard rule models, breaking the paradigms and serving as a support in the decision making of health professionals. 96.8% topic match

Develops an AI model for early sepsis prediction in ICU. Compares AI methods with traditional sepsis diagnosis indicators using various classifiers. Utilizes CRISP-DM methodology and cross-validation for model evaluation and selection.

Develops an AI model for early sepsis prediction in ICU. Compares AI methods with traditional sepsis diagnosis indicators using various classifiers. Utilizes CRISP-DM methodology and cross-validation for model evaluation and selection.

96.8%

0.0

2019

[80] SEPSIS SEVERITY PREDICTION USING MACHINE LEARNING Bhumika, ..., and Apoorva Journal Not Provided 2019 - 0 citations - Show abstract - Cite 96.8% topic match

Evaluates ML models for early sepsis detection in ICU. Focuses on bidirectional Long-Short Term Memory networks for predicting sepsis. Assessed on open and proprietary hospital databases for predictive performance.

Evaluates ML models for early sepsis detection in ICU. Focuses on bidirectional Long-Short Term Memory networks for predicting sepsis. Assessed on open and proprietary hospital databases for predictive performance.

96.7%

0.0

2023

[81] A Time Series Clinical Data-driven Preprocessing Approach to Early Sepsis Diagnosis SadikAref SadikAref, ..., and Sindhu Ghanta 2023 IEEE Conference on Artificial Intelligence (CAI) 2023 - 0 citations - Show abstract - Cite 96.7% topic match

Develops an AI model for early sepsis diagnosis. Utilizes machine learning with a unique segmentation method on a large dataset. Focuses on improving diagnosis sensitivity, critical for reducing mortality.

Develops an AI model for early sepsis diagnosis. Utilizes machine learning with a unique segmentation method on a large dataset. Focuses on improving diagnosis sensitivity, critical for reducing mortality.

96.7%

1.6

2019

[82] Representation Learning for Early Sepsis Prediction Luan V. Tran, ..., and Cyrus Shahabi 2019 Computing in Cardiology (CinC) 2019 - 8 citations - Show abstract - Cite 96.7% topic match

Proposes AEC-Net for early sepsis prediction using AI. Utilizes auto encoders and neural networks to analyze physiological data. Tested on large dataset; achieved notable results in a 2019 challenge.

Proposes AEC-Net for early sepsis prediction using AI. Utilizes auto encoders and neural networks to analyze physiological data. Tested on large dataset; achieved notable results in a 2019 challenge.

96.7%

0.0

2022

[83] A Sliding Window Approach for Early Prediction of Sepsis Begum Mutlu 2022 30th Signal Processing and Communications Applications Conference (SIU) 2022 - 0 citations - Show abstract - Cite 96.7% topic match

Introduces a sliding window approach for early sepsis prediction. Enhances machine learning efficacy using patients' demographics, vital signs, and lab results. Demonstrates significant performance improvement in early sepsis detection in ICU settings.

Introduces a sliding window approach for early sepsis prediction. Enhances machine learning efficacy using patients' demographics, vital signs, and lab results. Demonstrates significant performance improvement in early sepsis detection in ICU settings.

96.7%

1.8

2019

[84] Early Prediction of Sepsis: Using State-of-the-art Machine Learning Techniques on Vital Sign Inputs Manmay Nakhashi, ..., and Vikas C M 2019 Computing in Cardiology (CinC) 2019 - 9 citations - Show abstract - Cite 96.7% topic match

Provides an AI model for early sepsis detection in ICU patients. Utilizes a random forest-based machine learning technique on EHRs for prediction. Employs a utility metric score evaluating the effectiveness of early predictions.

Provides an AI model for early sepsis detection in ICU patients. Utilizes a random forest-based machine learning technique on EHRs for prediction. Employs a utility metric score evaluating the effectiveness of early predictions.

96.7%

3.7

2020

[85] Early Prediction of Sepsis From Clinical Data Using Ratio and Power-Based Features. Naimahmed Nesaragi and Shivnarayan Patidar Critical Care Medicine 2020 - 14 citations - Show abstract - Cite Abstract: OBJECTIVES Early prediction of sepsis is of utmost importance to provide optimal care at an early stage. This work aims to deploy soft-computing and machine learning techniques for early prediction of sepsis. DESIGN An algorithm for early identification of sepsis using ratio and power-based feature transformation of easily obtainable clinical data. SETTING PhysioNet Challenge 2019 provided ICU data from three separate hospital systems. Publicly shared data from two hospital systems are used for training and validation purposes, whereas sequestered data from all the three systems is used for testing. PATIENTS Over 60,000 ICU patients with up to 40 clinical variables are sourced for each hour of their ICU stay. The Sepsis-3 criterion is applied for annotation. INTERVENTIONS None. MEASUREMENTS AND MAIN RESULTS The clinical feature exploration for early prediction of sepsis is achieved using the proposed framework named genetic algorithm optimized ratio and power-based expert algorithm. An optimal feature set containing 46 ratio and power-based features is computed from the given patient covariates using genetic algorithm optimized ratio and power-based expert and grouped with identified 17 raw features and 55 statistical features to form a final feature set of 118 clinical features to predict the onset of sepsis in the proceeding 6 hours. The obtained features are fed to a hybrid Random Under-Sampling-Boosting algorithm, called RUSBoost for alleviating the involved class imbalance. The optimal RUSBoost model has achieved a normalized utility score of 0.318 on full test data. CONCLUSIONS The proposed study supports the realization of a hospital-specific customized solution in the form of an early-warning system for sepsis. However, an extended analysis is necessary to apply this framework for hospital-independent diagnosis of sepsis in general. Nevertheless, the clinical utility of hospital-specific customized solutions based on the proposed method across a wide range of hospital systems needs to be studied. 96.7% topic match

Introduces an AI model for early sepsis prediction. Utilizes machine learning with ratio and power-based features from ICU data. Tested using PhysioNet Challenge 2019 data from three hospital systems.

Introduces an AI model for early sepsis prediction. Utilizes machine learning with ratio and power-based features from ICU data. Tested using PhysioNet Challenge 2019 data from three hospital systems.

96.6%

0.0

2022

[86] A Novel Machine Learning Approach to predict Sepsis at an Early Stage N. Shanthi and A. A 2022 International Conference on Computer Communication and Informatics (ICCCI) 2022 - 0 citations - Show abstract - Cite 96.6% topic match

Develops machine learning algorithms to predict early-stage sepsis. Uses physiological data in models like Extreme Gradient Boost, Logistic Regression, and SVM. Implemented in VISUAL STUDIO with Python, focusing on ICU patient data.

Develops machine learning algorithms to predict early-stage sepsis. Uses physiological data in models like Extreme Gradient Boost, Logistic Regression, and SVM. Implemented in VISUAL STUDIO with Python, focusing on ICU patient data.

96.6%

1.9

2023

[87] Machine Learning for Early Prediction of Sepsis in Intensive Care Unit (ICU) Patients Abdullah Alanazi, ..., and B. Aldosari Medicina 2023 - 2 citations - Show abstract - Cite 96.6% topic match

Evaluates machine learning models for early sepsis prediction in ICU. Focuses on analyzing clinical data to predict sepsis signs earlier. Utilizes survival analysis and data mining, highlighting three significant factors.

Evaluates machine learning models for early sepsis prediction in ICU. Focuses on analyzing clinical data to predict sepsis signs earlier. Utilizes survival analysis and data mining, highlighting three significant factors.

96.6%

1.2

2020

[88] The role of waveform monitoring in Sepsis identification within the first hour of Intensive Care Unit stay Maximiliano Mollura, ..., and R. Barbieri 2020 11th Conference of the European Study Group on Cardiovascular Oscillations (ESGCO) 2020 - 5 citations - Show abstract - Cite 96.6% topic match

Demonstrates AI model's ability to identify Sepsis in ICU patients. Utilizes machine learning with waveform data from the MIMIC-III database for early Sepsis detection. Achieved significant measures: AUC=0.86, Specificity=0.85, Sensitivity=0.86, indicating high effectiveness.

Demonstrates AI model's ability to identify Sepsis in ICU patients. Utilizes machine learning with waveform data from the MIMIC-III database for early Sepsis detection. Achieved significant measures: AUC=0.86, Specificity=0.85, Sensitivity=0.86, indicating high effectiveness.

96.6%

0.0

2021

[89] A Novel Machine Learning Sepsis Prediction Algorithm for Intended ICU Use (NAVOY Sepsis): A Proof-of-Concept Study (Preprint) I. Persson, ..., and David Becedas https://doi.org/10.2196/preprints.28000 2021 - 0 citations - Show abstract - Cite Abstract: BACKGROUND Despite decades of research, sepsis remains a leading cause of mortality and morbidity in ICUs worldwide. The key to effective management and patient outcome is early detection, where no prospectively validated machine learning prediction algorithm is available for clinical use in Europe today. OBJECTIVE To develop a high-performance machine learning sepsis prediction algorithm based on routinely collected ICU data, designed to be implemented in Europe. METHODS The machine learning algorithm is developed using Convolutional Neural Network, based on the Massachusetts Institute of Technology Lab for Computational Physiology MIMIC-III Clinical Database, focusing on ICU patients aged 18 years or older. Twenty variables are used for prediction, on an hourly basis. Onset of sepsis is defined in accordance with the international Sepsis-3 criteria. RESULTS The developed algorithm NAVOY Sepsis uses 4 hours of input and can with high accuracy predict patients with high risk of developing sepsis in the coming hours. The prediction performance is superior to that of existing sepsis early warning scoring systems, and competes well with previously published prediction algorithms designed to predict sepsis onset in accordance with the Sepsis-3 criteria, as measured by the area under the receiver operating characteristics curve (AUROC) and the area under the precision-recall curve (AUPRC). NAVOY Sepsis yields AUROC = 0.90 and AUPRC = 0.62 for predictions up to 3 hours before sepsis onset. The predictive performance is externally validated on hold-out test data, where NAVOY Sepsis is confirmed to predict sepsis with high accuracy. CONCLUSIONS An algorithm with excellent predictive properties has been developed, based on variables routinely collected at ICUs. This algorithm is to be further validated in an ongoing prospective randomized clinical trial and will be CE marked as Software as a Medical Device, designed for commercial use in European ICUs. 96.6% topic match

Develops a machine learning sepsis prediction algorithm for ICU use. Uses Convolutional Neural Network and data from MIMIC-III, focusing on adult ICU patients. Aimed at early detection of sepsis, addressing a significant gap in current European clinical practice.

Develops a machine learning sepsis prediction algorithm for ICU use. Uses Convolutional Neural Network and data from MIMIC-III, focusing on adult ICU patients. Aimed at early detection of sepsis, addressing a significant gap in current European clinical practice.

96.5%

0.0

2023

[90] An Explainable AI based Clinical Assistance Model for Identifying Patients with the Onset of Sepsis Snehashis Chakraborty, ..., and S. Roy 2023 IEEE 24th International Conference on Information Reuse and Integration for Data Science (IRI) 2023 - 0 citations - Show abstract - Cite 96.5% topic match

Develops an AI-based model predicting sepsis in ICU patients. Focuses on early identification to enhance patient outcomes. Discusses the explanation capability of the AI model.

Develops an AI-based model predicting sepsis in ICU patients. Focuses on early identification to enhance patient outcomes. Discusses the explanation capability of the AI model.

96.5%

0.7

2021

[91] Predicting Sepsis in the Intensive Care Unit (ICU) through Vital Signs using Support Vector Machine (SVM) Zeina Rayan, ..., and Abdel-badeeh M. Salem The Open Bioinformatics Journal 2021 - 2 citations - Show abstract - Cite 96.5% topic match

Develops SVM model for early sepsis prediction in ICU. Model uses vital signs to predict sepsis with 0.73 accuracy. Focuses solely on the effectiveness of the SVM approach for early detection.

Develops SVM model for early sepsis prediction in ICU. Model uses vital signs to predict sepsis with 0.73 accuracy. Focuses solely on the effectiveness of the SVM approach for early detection.

96.5%

0.0

2019

[92] Early Detection of Sepsis Using Ensemblers Shailesh Nirgudkar and Tianyu Ding 2019 Computing in Cardiology (CinC) 2019 - 0 citations - Show abstract - Cite - PDF 96.5% topic match

Develops an AI model for early sepsis detection in ICU patients. Utilizes imputation, weak ensembler techniques, and 3-fold validation on a significant patient dataset. Achieved a utility score of 0.192 in a hidden test set, ranking 49 out of 79 in the Physionet 2019 challenge.

Develops an AI model for early sepsis detection in ICU patients. Utilizes imputation, weak ensembler techniques, and 3-fold validation on a significant patient dataset. Achieved a utility score of 0.192 in a hidden test set, ranking 49 out of 79 in the Physionet 2019 challenge.

96.5%

0.8

2019

[93] Machine Learning Algorithmic and System Level Considerations for Early Prediction of Sepsis Lakshman Narayanaswamy, ..., and R. Narayanswamy 2019 Computing in Cardiology (CinC) 2019 - 4 citations - Show abstract - Cite 96.5% topic match

Develops ML model for early sepsis prediction in ICU. Utilizes LSTM to analyze time-series patient data for prediction accuracy. Focuses on practical implementation in resource-limited settings, enhancing real-world applicability.

Develops ML model for early sepsis prediction in ICU. Utilizes LSTM to analyze time-series patient data for prediction accuracy. Focuses on practical implementation in resource-limited settings, enhancing real-world applicability.

96.4%

1.0

2019

[94] Time-Padded Random Forest Ensemble to Capture Changes in Physiology Leading to Sepsis Development B. Sweely, ..., and Xiaopeng Zhao 2019 Computing in Cardiology (CinC) 2019 - 5 citations - Show abstract - Cite 96.4% topic match

Develops a Random Forest AI model for early sepsis detection. Utilizes hourly patient data to predict sepsis development more effectively. Targets improvement in treatment timing and sepsis outcome in ICU settings.

Develops a Random Forest AI model for early sepsis detection. Utilizes hourly patient data to predict sepsis development more effectively. Targets improvement in treatment timing and sepsis outcome in ICU settings.

96.4%

0.0

2019

[95] Developing an Early Warning System for Sepsis Chloé Pou-Prom, ..., and David Dai Journal Not Provided 2019 - 0 citations - Show abstract - Cite 96.4% topic match

Develops an AI-based early sepsis detection system for ICU. Utilizes convolutional neural networks and random forest for prediction. Addresses class imbalance in data; model trained on 24-hour intervals.

Develops an AI-based early sepsis detection system for ICU. Utilizes convolutional neural networks and random forest for prediction. Addresses class imbalance in data; model trained on 24-hour intervals.

96.4%

0.5

2020

[96] AN EARLY PREDICTION AND DIAGNOSIS OF SEPSIS IN INTENSIVE CARE UNITS: AN UNSUPERVİSED MACHINE LEARNING MODEL Gökhan Silahtaroglu and Zehra Nur Canbolat Mugla Journal of Science and Technology 2020 - 2 citations - Show abstract - Cite 96.4% topic match

Develops an unsupervised AI model for early sepsis detection. Uses lactate and pH values from MIMIC-III to predict sepsis in ICU. Employs Fuzzy-C algorithm and PCA for data analysis and reduction.

Develops an unsupervised AI model for early sepsis detection. Uses lactate and pH values from MIMIC-III to predict sepsis in ICU. Employs Fuzzy-C algorithm and PCA for data analysis and reduction.

96.4%

1.1

2022

[97] Performance effectiveness of vital parameter combinations for early warning of sepsis—an exhaustive study using machine learning E. Rangan, ..., and M. Snyder JAMIA Open 2022 - 2 citations - Show abstract - Cite 96.4% topic match

Evaluates AI model, Vital-SEP, for early sepsis detection in ICU. Uses only 2 vital signs to predict sepsis up to 6 hours in advance. Suggests further study to assess clinical impacts and additional outcomes.

Evaluates AI model, Vital-SEP, for early sepsis detection in ICU. Uses only 2 vital signs to predict sepsis up to 6 hours in advance. Suggests further study to assess clinical impacts and additional outcomes.

96.3%

1.0

2019

[98] Cracking the “Sepsis” Code: Assessing Time Series Nature of EHR Data, and Using Deep Learning for Early Sepsis Prediction Soodabeh Sarafrazi, ..., and P. Francis-Lyon 2019 Computing in Cardiology (CinC) 2019 - 5 citations - Show abstract - Cite 96.3% topic match

Develops early sepsis prediction models using ICU data. Utilizes machine learning techniques to predict sepsis 12 hours beforehand. Highlights performance comparison, notably XGBoost's effectiveness over CNN-based models.

Develops early sepsis prediction models using ICU data. Utilizes machine learning techniques to predict sepsis 12 hours beforehand. Highlights performance comparison, notably XGBoost's effectiveness over CNN-based models.

96.3%

1.8

2021

[99] Exploring Features Contributing to the Early Prediction of Sepsis Using Machine Learning Esmaeil Shakeri, ..., and B. Far 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) 2021 - 5 citations - Show abstract - Cite 96.3% topic match

Evaluates AI models for early sepsis prediction using SHAP analysis. Analyzes important features from electronic health records for predicting sepsis onset in ICU settings. Investigates predictive model performance at different admission stages, highlighting challenges with data inconsistency.

Evaluates AI models for early sepsis prediction using SHAP analysis. Analyzes important features from electronic health records for predicting sepsis onset in ICU settings. Investigates predictive model performance at different admission stages, highlighting challenges with data inconsistency.

96.2%

0.3

2021

[100] Analysis of various health parameters for early and efficient prediction of sepsis A. Parashar, ..., and N. Rathee IOP Conference Series: Materials Science and Engineering 2021 - 1 citations - Show abstract - Cite 96.2% topic match

Provides analysis on early detection of sepsis using real-time data. Predicts sepsis onset 6 hours early with high accuracy and AUC scores. Utilizes demographic parameters and sensor data in its predictive model.

Provides analysis on early detection of sepsis using real-time data. Predicts sepsis onset 6 hours early with high accuracy and AUC scores. Utilizes demographic parameters and sensor data in its predictive model.

96.1%

0.0

2023

[101] NPRL: Nightly Profile Representation Learning for Early Sepsis Onset Prediction in ICU Trauma Patients Tucker Stewart, ..., and Juhua Hu 2023 IEEE International Conference on Big Data (BigData) 2023 - 0 citations - Show abstract - Cite - PDF 96.1% topic match

Develops a predictive AI framework for early sepsis detection. Predicts daily sepsis onset in ICU trauma patients using recent data. Addresses limitations in current methods by improving prediction timeliness and realism in deployment.

Develops a predictive AI framework for early sepsis detection. Predicts daily sepsis onset in ICU trauma patients using recent data. Addresses limitations in current methods by improving prediction timeliness and realism in deployment.

96.0%

0.0

2022

[102] Early prediction of generalized infection in intensive care units from clinical data: a committee-based machine learning approach Flávio Secco Fonseca, ..., and Wellington Pinheiros dos Santos 2022 IEEE Latin American Conference on Computational Intelligence (LA-CCI) 2022 - 0 citations - Show abstract - Cite 96.0% topic match

Proposes a hybrid AI model for early sepsis detection in ICUs. Utilizes a committee of classifiers, Gaussian distribution, and SMOTE method. Focuses on improving prediction using the PhysioNet database for validation.

Proposes a hybrid AI model for early sepsis detection in ICUs. Utilizes a committee of classifiers, Gaussian distribution, and SMOTE method. Focuses on improving prediction using the PhysioNet database for validation.

96.0%

1.5

2020

[103] Practical Machine Learning-Based Sepsis Prediction Michael J. Pettinati, ..., and N. Selvaraj 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) 2020 - 6 citations - Show abstract - Cite 96.0% topic match

Evaluates XGBoost models for sepsis prediction in ICU. Demonstrates performance variation with different feature sets, highlighting vital signs' importance. Focuses on AI-driven model adaptability and effectiveness using patient data subgroups.

Evaluates XGBoost models for sepsis prediction in ICU. Demonstrates performance variation with different feature sets, highlighting vital signs' importance. Focuses on AI-driven model adaptability and effectiveness using patient data subgroups.

95.8%

1.8

2019

[104] Early Prediction of Sepsis via SMOTE Upsampling and Mutual Information Based Downsampling Shiyu Liu, ..., and M. Motani 2019 Computing in Cardiology (CinC) 2019 - 9 citations - Show abstract - Cite 95.8% topic match

Proposes AI models to predict sepsis early in patients. Implements SMOTE and mutual information based downsampling for data imbalance. Ranked 77th with a utility score on test set; offers further improvements.

Proposes AI models to predict sepsis early in patients. Implements SMOTE and mutual information based downsampling for data imbalance. Ranked 77th with a utility score on test set; offers further improvements.

95.8%

0.6

2022

[105] Sub-Sequence Graph Representation Learning on High Variability Data for Dynamic Risk Prediction in Critical Care Ankur Teredesai, ..., and G. O’Keefe 2022 IEEE International Conference on Big Data (Big Data) 2022 - 1 citations - Show abstract - Cite Abstract: Sepsis is an extreme inflammatory response of the body to an infection. It is one of the leading causes of death in critical care and ICUs worldwide, resulting in approximately 25% mortality in critically ill populations. Early identification and intervention are crucial to reducing sepsis-associated mortality and improving patient prognosis because severe sepsis cases can lead to organ failure and other life-threatening complications. Diagnosis of Sepsis is challenging in terms of diagnostic accuracy and timeliness due to ambiguous symptoms and individual differences which are captured in heterogeneous varied data sources with irregular time sequences. In recent years, numerous efforts have been made using machine learning methods for sepsis prediction. However, there are still very limited successful industry scale implementations due to limitations of consistency of input data, which often does not fit the characteristics of uncertain time intervals and large number of missing values in real-world critical care settings. In this study, we demonstrate an innovative approach to predict sepsis occurrence in real-time, on heterogeneous sets of variables with multiple time-granularity, using a flexible graph structure to model patient health records. Our modeling task is to predict future sepsis risk at any time after the first 48 hours of admission using observations data from any time window within the past 12 hours. To the best of our knowledge, our proposed approach is the first ever implementation that is dynamic, uses a graph representation to overcome the problem of irregular input features, and offers continuous risk prediction, thereby improving the compatibility of the model in clinical settings. Unlike prior efforts that report results on de-identified curated public datasets with synthetic data filters, our experiments and results are validated by clinical experts, and are based on a large level-1 trauma center’s multi-year real-world longitudinal data. 95.8% topic match

Introduces an AI model for early sepsis prediction in ICU. Uses graph structure to model patient data and predict sepsis risk dynamically. Focuses on overcoming data inconsistency and missing values in critical care settings.

Introduces an AI model for early sepsis prediction in ICU. Uses graph structure to model patient data and predict sepsis risk dynamically. Focuses on overcoming data inconsistency and missing values in critical care settings.

95.7%

2.2

2012

[106] Imputation-Enhanced Prediction of Septic Shock in ICU Patients Joyce Ho, ..., and J. Ghosh Journal Not Provided 2012 - 28 citations - Show abstract - Cite 95.7% topic match

Enhances sepsis and septic shock prediction using AI. Utilizes imputation methods with AI models on a large ICU dataset. Focuses on non-invasive methods, improving the applicability in real-world ICU scenarios.

Enhances sepsis and septic shock prediction using AI. Utilizes imputation methods with AI models on a large ICU dataset. Focuses on non-invasive methods, improving the applicability in real-world ICU scenarios.

95.7%

1.1

2014

[107] Real-Time Predictive Analytics for Sepsis Level and Therapeutic Plans in Intensive Care Medicine João M. C. Gonçalves, ..., and Fernando Rua Int. J. Heal. Inf. Syst. Informatics 2014 - 11 citations - Show abstract - Cite 95.7% topic match

Provides evaluation of AI models for predicting sepsis levels in ICU. Utilizes Decision Trees, SVMs, and Naive Bayes for predictive analytics in sepsis detection. Achieved 100% accuracy in predicting sepsis level, less accuracy in therapeutic planning.

Provides evaluation of AI models for predicting sepsis levels in ICU. Utilizes Decision Trees, SVMs, and Naive Bayes for predictive analytics in sepsis detection. Achieved 100% accuracy in predicting sepsis level, less accuracy in therapeutic planning.

95.6%

3.1

2018

[108] Predictive Models of Sepsis in Adult ICU Patients Roman Z. Wang, ..., and L. Barnes 2018 IEEE International Conference on Healthcare Informatics (ICHI) 2018 - 19 citations - Show abstract - Cite 95.6% topic match

Provides predictive models of sepsis in ICU patients. Uses logistic regression, SVM, and LMT based on Sepsis-3 definition. Focuses on early detection using vital signs and blood culture results.

Provides predictive models of sepsis in ICU patients. Uses logistic regression, SVM, and LMT based on Sepsis-3 definition. Focuses on early detection using vital signs and blood culture results.

95.6%

0.6

2019

[109] Hybrid Feature Learning Using Autoencoders for Early Prediction of Sepsis Jia Yao, ..., and M. Motani 2019 Computing in Cardiology (CinC) 2019 - 3 citations - Show abstract - Cite 95.6% topic match

Proposes AI method for early sepsis prediction in ICU. Utilizes autoencoders to learn spatial-temporal data for sepsis detection. Ranked 77th in 2019 PhysioNet Challenge; discusses potential improvement areas.

Proposes AI method for early sepsis prediction in ICU. Utilizes autoencoders to learn spatial-temporal data for sepsis detection. Ranked 77th in 2019 PhysioNet Challenge; discusses potential improvement areas.

95.6%

0.6

2021

[110] More Generalizable Models For Sepsis Detection Under Covariate Shift. Jifan Gao, ..., and Guanhua Chen AMIA ... Annual Symposium proceedings. AMIA Symposium 2021 - 2 citations - Show abstract - Cite - PDF 95.6% topic match

Evaluates covariate shift corrections in ML models for sepsis detection. Shows enhanced model generalizability for early sepsis detection in ICU patients. Focuses specifically on AI’s role in overcoming prediction challenges under covariate shift scenarios.

Evaluates covariate shift corrections in ML models for sepsis detection. Shows enhanced model generalizability for early sepsis detection in ICU patients. Focuses specifically on AI’s role in overcoming prediction challenges under covariate shift scenarios.

95.5%

1.3

2019

[111] Early Prediction of Sepsis from Clinical Data Using Artificial Intelligence R Murat Demirer and Oya Demirer 2019 Scientific Meeting on Electrical-Electronics & Biomedical Engineering and Computer Science (EBBT) 2019 - 7 citations - Show abstract - Cite 95.5% topic match

Develops AI models for early sepsis prediction in patients. Utilizes POMDPs, spectral analysis, and patient data to forecast sepsis. Focuses on reducing sepsis-associated hospital mortality through early detection.

Develops AI models for early sepsis prediction in patients. Utilizes POMDPs, spectral analysis, and patient data to forecast sepsis. Focuses on reducing sepsis-associated hospital mortality through early detection.

95.5%

1.0

2021

[112] Comparison of Two Predictive Models of Sepsis in Critically Ill Patients Based on the Combined Use of Inflammatory Markers Xiaoming Li, ..., and Feihu Zhou International Journal of General Medicine 2021 - 3 citations - Show abstract - Cite 95.5% topic match

Develops AI predictive models for early sepsis detection in ICU. Uses inflammatory markers to validate a nomogram and scoring model in ICU patients. Assesses model performance using ROC curves and AUC metrics.

Develops AI predictive models for early sepsis detection in ICU. Uses inflammatory markers to validate a nomogram and scoring model in ICU patients. Assesses model performance using ROC curves and AUC metrics.

95.4%

0.0

2019

[113] Real-time diagnosis of sepsis in intensive care using Logistic regression and Cox proportional hazards model Fernando Andreotti, ..., and A. Szabo Journal Not Provided 2019 - 0 citations - Show abstract - Cite 95.4% topic match

Provides evaluation of ML methods for early sepsis detection. Uses Logistic regression and Cox models with ICU patient data from Physionet 2019. Focuses on real-time diagnosis from electronic patient records in ICUs.

Provides evaluation of ML methods for early sepsis detection. Uses Logistic regression and Cox models with ICU patient data from Physionet 2019. Focuses on real-time diagnosis from electronic patient records in ICUs.

95.3%

9.1

2023

[114] Deployment of machine learning algorithms to predict sepsis: systematic review and application of the SALIENT clinical AI implementation framework A. V. D. Vegt, ..., and Paul J. Lane Journal of the American Medical Informatics Association : JAMIA 2023 - 11 citations - Show abstract - Cite 95.3% topic match

Provides a systematic review of AI-based sepsis prediction algorithms. Evaluates deployment, methodological quality, and outcomes of AI in predicting sepsis in adult hospital settings. Identifies barriers and enablers for implementation, assessing impact on mortality in some studies.

Provides a systematic review of AI-based sepsis prediction algorithms. Evaluates deployment, methodological quality, and outcomes of AI in predicting sepsis in adult hospital settings. Identifies barriers and enablers for implementation, assessing impact on mortality in some studies.

95.1%

0.0

2021

[115] An Interpretable Early Dynamic Sequential Predictor for Sepsis-Induced Coagulopathy Progression in the Real-World Using Machine Learning Ruixia Cui, ..., and Chang Liu Frontiers in Medicine 2021 - 0 citations - Show abstract - Cite 95.1% topic match

Develops AI models for early detection of sepsis-induced complications. Implements machine learning to predict sepsis-induced coagulopathy (SIC) hours before onset. Evaluated using area under the receiver operating characteristic curve (AUROC) metrics across multiple datasets.

Develops AI models for early detection of sepsis-induced complications. Implements machine learning to predict sepsis-induced coagulopathy (SIC) hours before onset. Evaluated using area under the receiver operating characteristic curve (AUROC) metrics across multiple datasets.

95.1%

0.6

2019

[116] Diagnosis of Sepsis Using Ratio Based Features Shivnarayan Patidar 2019 Computing in Cardiology (CinC) 2019 - 3 citations - Show abstract - Cite 95.1% topic match

Develops an AI model for early sepsis prediction in critical care. Uses genetic algorithm for feature selection to enhance model accuracy. Evaluated using the 2019 PhysioNet/CinC Challenge dataset, achieving a utility score of 30.9%.

Develops an AI model for early sepsis prediction in critical care. Uses genetic algorithm for feature selection to enhance model accuracy. Evaluated using the 2019 PhysioNet/CinC Challenge dataset, achieving a utility score of 30.9%.

95.0%

8.6

2018

[117] Early Prediction of Sepsis in EMR Records Using Traditional ML Techniques and Deep Learning LSTM Networks Mohammed Saqib, ..., and May D. Wang 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) 2018 - 52 citations - Show abstract - Cite 95.0% topic match

Explores ML and LSTM for early sepsis prediction using EMRs. Analyzes first 24 and 36 hours of ICU patient data for model training. Reports success with traditional ML achieving an AUC-ROC of 0.696.

Explores ML and LSTM for early sepsis prediction using EMRs. Analyzes first 24 and 36 hours of ICU patient data for model training. Reports success with traditional ML achieving an AUC-ROC of 0.696.

95.0%

0.0

2022

[118] Risk Management In Intensive Care Units With Artificial Intelligence Technologies: Systematic Review of Prediction Models Using Electronic Health Records Zuhal Çayirtepe and A. Şenel Journal of Basic and Clinical Health Sciences 2022 - 0 citations - Show abstract - Cite 95.0% topic match

Reviews AI-driven prediction models for ICU risks, including sepsis. Includes four studies on sepsis prediction using electronic health records (EHRs). Indicates AI models outperform traditional risk models, enhancing ICU patient safety.

Reviews AI-driven prediction models for ICU risks, including sepsis. Includes four studies on sepsis prediction using electronic health records (EHRs). Indicates AI models outperform traditional risk models, enhancing ICU patient safety.

94.7%

0.0

2021

[119] Predicting infection and sepsis; what predictors have been used to train machine learning algorithms? A systematic review N. Hassan, ..., and S. Slight International Journal of Pharmacy Practice 2021 - 0 citations - Show abstract - Cite Abstract: Sepsis is a life-threatening condition that is associated with increased mortality. Artificial intelligence tools can inform clinical decision making by flagging patients who may be at risk of developing infection and subsequent sepsis and assist clinicians with their care management. To identify the optimal set of predictors used to train machine learning algorithms to predict the likelihood of an infection and subsequent sepsis and inform clinical decision making. This systematic review was registered in PROSPERO database (CRD42020158685). We searched 3 large databases: Medline, Cumulative Index of Nursing and Allied Health Literature, and Embase, using appropriate search terms. We included quantitative primary research studies that focused on sepsis prediction associated with bacterial infection in adult population (>18 years) in all care settings, which included data on predictors to develop machine learning algorithms. The timeframe of the search was 1st January 2000 till the 25th November 2019. Data extraction was performed using a data extraction sheet, and a narrative synthesis of eligible studies was undertaken. Narrative analysis was used to arrange the data into key areas, and compare and contrast between the content of included studies. Quality assessment was performed using Newcastle-Ottawa Quality Assessment scale, which was used to evaluate the quality of non-randomized studies. Bias was not assessed due to the non-randomised nature of the included studies. Fifteen articles met our inclusion criteria (Figure 1). We identified 194 predictors that were used to train machine learning algorithms to predict infection and subsequent sepsis, with 13 predictors used on average across all included studies. The most significant predictors included age, gender, smoking, alcohol intake, heart rate, blood pressure, lactate level, cardiovascular disease, endocrine disease, cancer, chronic kidney disease (eGFR<60ml/min), white blood cell count, liver dysfunction, surgical approach (open or minimally invasive), and pre-operative haematocrit < 30%. These predictors were used for the development of all the algorithms in the fifteen articles. All included studies used artificial intelligence techniques to predict the likelihood of sepsis, with average sensitivity 77.5±19.27, and average specificity 69.45±21.25. The type of predictors used were found to influence the predictive power and predictive timeframe of the developed machine learning algorithm. Two strengths of our review were that we included studies published since the first definition of sepsis was published in 2001, and identified factors that can improve the predictive ability of algorithms. However, we note that the included studies had some limitations, with three studies not validating the models that they developed, and many tools limited by either their reduced specificity or sensitivity or both. This work has important implications for practice, as predicting the likelihood of sepsis can help inform the management of patients and concentrate finite resources to those patients who are most at risk. Producing a set of predictors can also guide future studies in developing more sensitive and specific algorithms with increased predictive time window to allow for preventive clinical measures. 94.7% topic match

Reviews AI predictors for sepsis detection from infections. Analyzes various predictors used in machine learning for early sepsis indication. Focuses on adult patients across various care settings, not just ICU.

Reviews AI predictors for sepsis detection from infections. Analyzes various predictors used in machine learning for early sepsis indication. Focuses on adult patients across various care settings, not just ICU.

94.7%

0.6

2019

[120] Interpretation of Artificial Intelligence Algorithms in the Prediction of Sepsis Induparkavi Murugesan, ..., and Malathi Arumugam 2019 Computing in Cardiology (CinC) 2019 - 3 citations - Show abstract - Cite 94.7% topic match

Investigates AI decision-making in sepsis prediction. Explores interpretability of AI algorithms using clinical records for sepsis detection. Ranked 59th in the PhysioNet challenge; utility score was 0.131.

Investigates AI decision-making in sepsis prediction. Explores interpretability of AI algorithms using clinical records for sepsis detection. Ranked 59th in the PhysioNet challenge; utility score was 0.131.

94.6%

0.4

2019

[121] Prediction of Sepsis from Clinical Data Using LSTM and XGBoost Yongchao Wang, ..., and Xu Ma Journal Not Provided 2019 - 2 citations - Show abstract - Cite 94.6% topic match

94.5%

0.0

2019

[122] Convolutional neural networks based model to provide early prediction of sepsis from Clinical Data M. Baydoun, ..., and El-Hajj Journal Not Provided 2019 - 0 citations - Show abstract - Cite 94.5% topic match

94.5%

2.2

2023

[123] Machine Learning-Based Early Prediction of Sepsis Using Electronic Health Records: A Systematic Review K. R. Islam, ..., and M. E. Chowdhury Journal of Clinical Medicine 2023 - 2 citations - Show abstract - Cite 94.5% topic match

Provides a systematic review on ML/DL predictions of sepsis. Focuses on early detection using EHRs in adult populations across various settings. Highlights the use of longitudinal data for predictive accuracy; mainly retrospective studies.

Provides a systematic review on ML/DL predictions of sepsis. Focuses on early detection using EHRs in adult populations across various settings. Highlights the use of longitudinal data for predictive accuracy; mainly retrospective studies.

94.3%

1.5

2020

[124] Prediction of Septic Shock Onset in ICU by Instantaneous Monitoring of Vital Signs* Maximiliano Mollura, ..., and R. Barbieri 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) 2020 - 6 citations - Show abstract - Cite 94.3% topic match

94.1%

0.0

2023

[125] Feature Selection using Generalized Linear Model for Machine Learning-based Sepsis Prediction Mohammed Ashikur Rahman, ..., and A. Tumian 2023 International Conference on Advances in Intelligent Computing and Applications (AICAPS) 2023 - 0 citations - Show abstract - Cite 94.1% topic match

Provides AI-based sepsis prediction model evaluation in ICU patients. Uses GLM for feature selection, improving machine learning model accuracy. Compares model performance to traditional clinical severity scores using AUROC.

Provides AI-based sepsis prediction model evaluation in ICU patients. Uses GLM for feature selection, improving machine learning model accuracy. Compares model performance to traditional clinical severity scores using AUROC.

94.1%

0.0

2023

[126] Early Prediction of Neonatal Sepsis From Synthetic Clinical Data Using Machine Learning Simon Lyra, ..., and Markus J. Lüken 2023 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) 2023 - 0 citations - Show abstract - Cite 94.1% topic match

Demonstrates ML models predicting neonatal sepsis using synthetic data. Achieved AUROC of 0.91 indicating high model accuracy in early prediction. Focuses on neonates, not adult ICU patients; uses synthetic data augmentation.

Demonstrates ML models predicting neonatal sepsis using synthetic data. Achieved AUROC of 0.91 indicating high model accuracy in early prediction. Focuses on neonates, not adult ICU patients; uses synthetic data augmentation.

94.0%

0.0

2023

[127] Artificial Intelligence in Laboratory Technologies for Early Detection and Prognostication of Sepsis: A Systematic Review Mohsen Bakouri, ..., and Megren A. Alqahtani Journal of Pioneering Medical Science 2023 - 0 citations - Show abstract - Cite Abstract: Background: Sepsis: a complex clinical syndrome--represents life-threatening organ dysfunction instigated by an infection's dysregulated host response. Early detection and accurate prognostication of sepsis are crucial; they pave the way for timely intervention, ultimately enhancing patient outcomes. The rise in interest towards Artificial Intelligence (AI) applications within laboratory technologies is directly related to its potential for improving early detection and prognosis forecasting in sepsis cases; this interest comes as AI continues its advancement. Methods: We conducted a systematic review of studies utilizing AI algorithms in laboratory settings for early sepsis detection and prognostication: our methods entailed searching relevant databases for research published until October 2023. Our inclusion criteria spanned original articles; these applied machine learning (ML) and deep learning (DL) techniques to laboratory data--with the aim being sepsis prediction. We assessed the quality of the studies, extracted and synthesized data on AI model performance metrics - including: area under receiver operating characteristic curve (AUROC), sensitivity, specificity, and accuracy. Results: The review encompassed eight studies meeting the inclusion criteria; AI models showcased exceptional predictive capabilities--evidenced by a range of AUROC values from 0.799 to 0.9213, signifying noticeably acceptable performance. However, there was wide variation in sensitivity and specificity among these analyses: an indicator of heterogeneity in model performance. Superior prognostic accuracy and potential for real-time monitoring of patients' early sepsis signs emerged in several models: notably, within the first 12 hours of patient admission - their highest predictive period. The models frequently outperformed traditional scoring systems. Conclusion: Laboratory technology's AI applications significantly promise sepsis' early detection and prognostication. Reviewed studies suggest AI models may surpass traditional methods, offering potential integration into clinical workflows for rapid sepsis identification aid. Nevertheless, we also acknowledged both the variability in model performance and necessity of additional validation across diverse clinical settings. Future research: it must concentrate on two key aspects--the refinement of AI algorithms to enhance sensitivity and precision; furthermore, it should delve into evaluating the clinical impact of tools for sepsis prediction that are assisted by AI. 94.0% topic match

Evaluates AI in lab technologies for sepsis early detection. Shows AI models may outperform traditional methods in rapid sepsis identification. Highlights need for further AI refinement and clinical impact evaluation.

Evaluates AI in lab technologies for sepsis early detection. Shows AI models may outperform traditional methods in rapid sepsis identification. Highlights need for further AI refinement and clinical impact evaluation.

94.0%

0.0

2021

[128] Machine Learning for clinical course analysis in septic patients P. Ferreira Journal Not Provided 2021 - 0 citations - Show abstract - Cite 94.0% topic match

Develops ML models to predict septic shock in ICU patients. Utilizes both supervised and unsupervised learning on data from two sources. Focuses on septic shock, a severe result of unmanaged sepsis.

Develops ML models to predict septic shock in ICU patients. Utilizes both supervised and unsupervised learning on data from two sources. Focuses on septic shock, a severe result of unmanaged sepsis.

94.0%

6.3

2021

[129] A Machine-Learning Approach for Dynamic Prediction of Sepsis-Induced Coagulopathy in Critically Ill Patients With Sepsis Qin-yu Zhao, ..., and Zhe Luo Frontiers in Medicine 2021 - 22 citations - Show abstract - Cite Abstract: Background: Sepsis-induced coagulopathy (SIC) denotes an increased mortality rate and poorer prognosis in septic patients. Objectives: Our study aimed to develop and validate machine-learning models to dynamically predict the risk of SIC in critically ill patients with sepsis. Methods: Machine-learning models were developed and validated based on two public databases named Medical Information Mart for Intensive Care (MIMIC)-IV and the eICU Collaborative Research Database (eICU-CRD). Dynamic prediction of SIC involved an evaluation of the risk of SIC each day after the diagnosis of sepsis using 15 predictive models. The best model was selected based on its accuracy and area under the receiver operating characteristic curve (AUC), followed by fine-grained hyperparameter adjustment using the Bayesian Optimization Algorithm. A compact model was developed, based on 15 features selected according to their importance and clinical availability. These two models were compared with Logistic Regression and SIC scores in terms of SIC prediction. Results: Of 11,362 patients in MIMIC-IV included in the final cohort, a total of 6,744 (59%) patients developed SIC during sepsis. The model named Categorical Boosting (CatBoost) had the greatest AUC in our study (0.869; 95% CI: 0.850–0.886). Coagulation profile and renal function indicators were the most important features for predicting SIC. A compact model was developed with an AUC of 0.854 (95% CI: 0.832–0.872), while the AUCs of Logistic Regression and SIC scores were 0.746 (95% CI: 0.735–0.755) and 0.709 (95% CI: 0.687–0.733), respectively. A cohort of 35,252 septic patients in eICU-CRD was analyzed. The AUCs of the full and the compact models in the external validation were 0.842 (95% CI: 0.837–0.846) and 0.803 (95% CI: 0.798–0.809), respectively, which were still larger than those of Logistic Regression (0.660; 95% CI: 0.653–0.667) and SIC scores (0.752; 95% CI: 0.747–0.757). Prediction results were illustrated by SHapley Additive exPlanations (SHAP) values, which made our models clinically interpretable. Conclusions: We developed two models which were able to dynamically predict the risk of SIC in septic patients better than conventional Logistic Regression and SIC scores. 94.0% topic match

Develops AI models for predicting SIC in sepsis patients. Utilizes dynamic daily risk assessments using data from MIMIC-IV and eICU-CRD. Focuses specifically on Sepsis-Induced Coagulopathy, not sepsis detection.

Develops AI models for predicting SIC in sepsis patients. Utilizes dynamic daily risk assessments using data from MIMIC-IV and eICU-CRD. Focuses specifically on Sepsis-Induced Coagulopathy, not sepsis detection.

93.9%

7.4

2019

[130] Machine Learning Models for Analysis of Vital Signs Dynamics: A Case for Sepsis Onset Prediction Eli Bloch, ..., and Y. Aperstein Journal of Healthcare Engineering 2019 - 35 citations - Show abstract - Cite 93.9% topic match

93.9%

4.4

2021

[131] A Machine Learning Sepsis Prediction Algorithm for Intended Intensive Care Unit Use (NAVOY Sepsis): Proof-of-Concept Study I. Persson, ..., and David Becedas JMIR Formative Research 2021 - 15 citations - Show abstract - Cite 93.9% topic match

93.9%

0.0

2018

[132] Predicting Sepsis-Induced Patient Deterioration Using Machine Learning Menno Liefstingh Journal Not Provided 2018 - 0 citations - Show abstract - Cite 93.9% topic match

93.9%

0.1

2014

[133] Computing network-based features from physiological time series: Application to sepsis detection S. Santaniello, ..., and R. Winslow 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society 2014 - 1 citations - Show abstract - Cite 93.9% topic match

Provides a novel network-based approach to sepsis detection in ICUs. Uses physiological time series from ICU patients to explore dynamic interactions and identify sepsis. Focuses on interaction analysis rather than direct AI-driven predictive modeling for early detection.

Provides a novel network-based approach to sepsis detection in ICUs. Uses physiological time series from ICU patients to explore dynamic interactions and identify sepsis. Focuses on interaction analysis rather than direct AI-driven predictive modeling for early detection.

93.8%

14.8

2023

[134] Ignore, Trust, or Negotiate: Understanding Clinician Acceptance of AI-Based Treatment Recommendations in Health Care Venkatesh Sivaraman, ..., and Adam Perer Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems 2023 - 22 citations - Show abstract - Cite - PDF 93.8% topic match

Develops AI interface for sepsis treatment recommendations. Examines ICU clinicians' acceptance and interaction with AI for sepsis decisions. Highlights negotiation between AI suggestions and clinicians' judgment, impacting AI adoption.

Develops AI interface for sepsis treatment recommendations. Examines ICU clinicians' acceptance and interaction with AI for sepsis decisions. Highlights negotiation between AI suggestions and clinicians' judgment, impacting AI adoption.

93.8%

7.3

2020

[135] An interpretable deep-learning model for early prediction of sepsis in the emergency department Dongdong Zhang, ..., and Ping Zhang Patterns 2020 - 28 citations - Show abstract - Cite 93.8% topic match

Develops an AI model for early sepsis prediction in the emergency department. Utilized over 100,000 patient records to predict sepsis onset 4 hours before diagnosis. Focuses on the emergency department, not exclusively on ICU patients.

Develops an AI model for early sepsis prediction in the emergency department. Utilized over 100,000 patient records to predict sepsis onset 4 hours before diagnosis. Focuses on the emergency department, not exclusively on ICU patients.

93.8%

0.8

2018

[136] Semantically Enhanced Dynamic Bayesian Network for Detecting Sepsis Mortality Risk in ICU Patients with Infection Tony Wang, ..., and Joy Hardison ArXiv 2018 - 5 citations - Show abstract - Cite - PDF 93.8% topic match

Develops a DBN for predicting sepsis mortality risk in ICU. Compares DBN's predictive accuracy with existing clinical scoring tools. Utilizes structured and unstructured data for dynamic risk modeling.

Develops a DBN for predicting sepsis mortality risk in ICU. Compares DBN's predictive accuracy with existing clinical scoring tools. Utilizes structured and unstructured data for dynamic risk modeling.

93.8%

0.0

2016

[137] Computational prediction of clinical outcome of sepsis from critical care database ( Life Sciences S. Pfohl Journal Not Provided 2016 - 0 citations - Show abstract - Cite 93.8% topic match

Provides a computational pipeline for early sepsis detection. Utilizes full data from MIMIC-III for feature extraction in predicting sepsis. Demonstrates high performance in retrospective sepsis identification and mortality risk prediction.

Provides a computational pipeline for early sepsis detection. Utilizes full data from MIMIC-III for feature extraction in predicting sepsis. Demonstrates high performance in retrospective sepsis identification and mortality risk prediction.

93.7%

0.0

2019

[138] Development of an Early Warning System for Sepsis Chloé Pou-Prom, ..., and David Dai 2019 Computing in Cardiology (CinC) 2019 - 0 citations - Show abstract - Cite 93.7% topic match

93.7%

1.1

2023

[139] A Machine Learning-Based Algorithm for Early Detection of Sepsis in Hospitalized Patients: Development and Evaluation Venkata Raghuveer Burugadda, ..., and Neha Bhati 2023 1st International Conference on Circuits, Power and Intelligent Systems (CCPIS) 2023 - 1 citations - Show abstract - Cite 93.7% topic match

93.6%

0.8

2019

[140] Early Prediction of Sepsis Considering Early Warning Scoring Systems P. Biglarbeigi, ..., and J. Mclaughlin 2019 Computing in Cardiology (CinC) 2019 - 4 citations - Show abstract - Cite 93.6% topic match

93.6%

46.7

2016

[141] Prediction of Sepsis in the Intensive Care Unit With Minimal Electronic Health Record Data: A Machine Learning Approach Thomas Desautels, ..., and R. Das JMIR Medical Informatics 2016 - 365 citations - Show abstract - Cite Abstract: Background Sepsis is one of the leading causes of mortality in hospitalized patients. Despite this fact, a reliable means of predicting sepsis onset remains elusive. Early and accurate sepsis onset predictions could allow more aggressive and targeted therapy while maintaining antimicrobial stewardship. Existing detection methods suffer from low performance and often require time-consuming laboratory test results. Objective To study and validate a sepsis prediction method, InSight, for the new Sepsis-3 definitions in retrospective data, make predictions using a minimal set of variables from within the electronic health record data, compare the performance of this approach with existing scoring systems, and investigate the effects of data sparsity on InSight performance. Methods We apply InSight, a machine learning classification system that uses multivariable combinations of easily obtained patient data (vitals, peripheral capillary oxygen saturation, Glasgow Coma Score, and age), to predict sepsis using the retrospective Multiparameter Intelligent Monitoring in Intensive Care (MIMIC)-III dataset, restricted to intensive care unit (ICU) patients aged 15 years or more. Following the Sepsis-3 definitions of the sepsis syndrome, we compare the classification performance of InSight versus quick sequential organ failure assessment (qSOFA), modified early warning score (MEWS), systemic inflammatory response syndrome (SIRS), simplified acute physiology score (SAPS) II, and sequential organ failure assessment (SOFA) to determine whether or not patients will become septic at a fixed period of time before onset. We also test the robustness of the InSight system to random deletion of individual input observations. Results In a test dataset with 11.3% sepsis prevalence, InSight produced superior classification performance compared with the alternative scores as measured by area under the receiver operating characteristic curves (AUROC) and area under precision-recall curves (APR). In detection of sepsis onset, InSight attains AUROC = 0.880 (SD 0.006) at onset time and APR = 0.595 (SD 0.016), both of which are superior to the performance attained by SIRS (AUROC: 0.609; APR: 0.160), qSOFA (AUROC: 0.772; APR: 0.277), and MEWS (AUROC: 0.803; APR: 0.327) computed concurrently, as well as SAPS II (AUROC: 0.700; APR: 0.225) and SOFA (AUROC: 0.725; APR: 0.284) computed at admission (P<.001 for all comparisons). Similar results are observed for 1-4 hours preceding sepsis onset. In experiments where approximately 60% of input data are deleted at random, InSight attains an AUROC of 0.781 (SD 0.013) and APR of 0.401 (SD 0.015) at sepsis onset time. Even with 60% of data missing, InSight remains superior to the corresponding SIRS scores (AUROC and APR, P<.001), qSOFA scores (P=.0095; P<.001) and superior to SOFA and SAPS II computed at admission (AUROC and APR, P<.001), where all of these comparison scores (except InSight) are computed without data deletion. Conclusions Despite using little more than vitals, InSight is an effective tool for predicting sepsis onset and performs well even with randomly missing data. 93.6% topic match

93.6%

2.1

2018

[142] Machine Learning Methods for Septic Shock Prediction Aiman Darwiche and Sumitra Mukherjee International Conference on Artificial Intelligence and Virtual Reality 2018 - 12 citations - Show abstract - Cite 93.6% topic match

93.6%

5.9

2021

[143] Predicting in-hospital mortality in ICU patients with sepsis using gradient boosting decision tree Ke Li, ..., and Jialin Liu Medicine 2021 - 19 citations - Show abstract - Cite 93.6% topic match

Examines ICU sepsis mortality prediction using gradient boosting. Focuses on predicting mortality among sepsis patients in ICUs via AI models. Discusses gap in AI algorithm implementation, not specifically early detection of sepsis onset.

Examines ICU sepsis mortality prediction using gradient boosting. Focuses on predicting mortality among sepsis patients in ICUs via AI models. Discusses gap in AI algorithm implementation, not specifically early detection of sepsis onset.

93.6%

0.0

2022

[144] A machine learning based predictive model for the diagnosis of sepsis Juan A. Delgado Sanchis, ..., and J. García-Giménez medRxiv 2022 - 0 citations - Show abstract - Cite 93.6% topic match

Introduces a machine learning model for early sepsis diagnosis. Utilizes gradient boosting with biochemical markers for reliable identification. Focuses on entry in the emergency room, not specifically ICU settings.

Introduces a machine learning model for early sepsis diagnosis. Utilizes gradient boosting with biochemical markers for reliable identification. Focuses on entry in the emergency room, not specifically ICU settings.

93.6%

8.6

2001

[145] Artificial intelligence applications in the intensive care unit C. William, ..., and M. F. F. T. T. P. Bryan E. Marshall Critical Care Medicine 2001 - 202 citations - Show abstract - Cite 93.6% topic match

93.5%

2.4

2019

[146] Retrospective Observational Study of the Clinical Performance Characteristics of a Machine Learning Approach to Early Sepsis Identification R. Topiwala, ..., and B. Meisenberg Critical Care Explorations 2019 - 12 citations - Show abstract - Cite 93.5% topic match

Evaluates an AI sepsis prediction tool in a clinical setting. Assessed AI's performance on early sepsis detection versus clinician recognition. Focus on emergency and inpatient settings, not specifically ICU.

Evaluates an AI sepsis prediction tool in a clinical setting. Assessed AI's performance on early sepsis detection versus clinician recognition. Focus on emergency and inpatient settings, not specifically ICU.

93.5%

10.4

2021

[147] Early Detection of Sepsis With Machine Learning Techniques: A Brief Clinical Perspective D. Giacobbe, ..., and M. Bassetti Frontiers in Medicine 2021 - 36 citations - Show abstract - Cite 93.5% topic match

Provides a clinician's perspective on AI for early sepsis detection. Discusses AI model development challenges, including sepsis definition and data input. Highlights AI's potential and pitfalls in improving sepsis prediction and clinical decision-making.

Provides a clinician's perspective on AI for early sepsis detection. Discusses AI model development challenges, including sepsis definition and data input. Highlights AI's potential and pitfalls in improving sepsis prediction and clinical decision-making.

93.3%

10.7

2021

[148] DeepAISE - An interpretable and recurrent neural survival model for early prediction of sepsis S. Shashikumar, ..., and S. Nemati Artificial intelligence in medicine 2021 - 37 citations - Show abstract - Cite 93.3% topic match

93.2%

5.3

2019

[149] A Data-Driven Approach to Predicting Septic Shock in the Intensive Care Unit Christopher R. Yee, ..., and V. Vemulapalli Biomedical Informatics Insights 2019 - 25 citations - Show abstract - Cite 93.2% topic match

93.1%

0.2

2018

[150] Effect of a Sepsis Prediction Algorithm on Patient Mortality, Length of Stay, and Readmission Hoyt J Burdick, ..., and R. Das bioRxiv 2018 - 1 citations - Show abstract - Cite Abstract: Objective To validate performance of a machine learning algorithm for severe sepsis determination up to 48 hours before onset, and to evaluate the effect of the algorithm on in-hospital mortality, hospital length of stay, and 30-day readmission. Setting This cohort study includes a combined retrospective analysis and clinical outcomes evaluation: a dataset containing 510,497 patient encounters from 461 United States health centers for retrospective analysis, and a multiyear, multicenter clinical data set of real-world data containing 75,147 patient encounters from nine hospitals for clinical outcomes evaluation. Participants For retrospective analysis, 270,438 adult patients with at least one documented measurement of five out of six vital sign measurements were included. For clinical outcomes analysis, 17,758 adult patients who met two or more Systemic Inflammatory Response Syndrome (SIRS) criteria at any point during their stay were included. Results At severe sepsis onset, the MLA demonstrated an AUROC of 0.91 (95% CI 0.90, 0.92), which exceeded those of MEWS (0.71, P<001), SOFA (0.74; P<.001), and SIRS (0.62; P<.001). For severe sepsis prediction 48 hours in advance of onset, the MLA achieved an AUROC of 0.77 (95% CI 0.73, 0.80). For the clinical outcomes study, when using the MLA, hospitals saw an average 39.5% reduction of in-hospital mortality, a 32.3% reduction in hospital length of stay, and a 22.7% reduction in 30-day readmission rate. Conclusions The MLA accurately predicts severe sepsis onset up to 48 hours in advance using only readily available vital signs in retrospective validation. Reductions of in-hospital mortality, hospital length of stay, and 30-day readmissions were observed in real-world clinical use of the MLA. Results suggest this system may improve severe sepsis detection and patient outcomes over the use of rules-based sepsis detection systems. KEY POINTS Question Is a machine learning algorithm capable of accurate severe sepsis prediction, and does its clinical implementation improve patient mortality rates, hospital length of stay, and 30-day readmission rates? Findings In a retrospective analysis that included datasets containing a total of 585,644 patient encounters from 461 hospitals, the machine learning algorithm demonstrated an AUROC of 0.93 at time of severe sepsis onset, which exceeded those of MEWS (0.71), SOFA (0.74), and SIRS (0.62); and an AUROC of 0.77 for severe sepsis prediction 48 hours in advance of onset. In an analysis of real-world data from nine hospitals across 75,147 patient encounters, use of the machine learning algorithm was associated with a 39.5% reduction in in-hospital mortality, a 32.3% reduction in hospital length of stay, and a 22.7% reduction in 30-day readmission rate. Meaning The accurate and predictive nature of this algorithm may encourage early recognition of patients trending toward severe sepsis, and therefore improve sepsis related outcomes. STRENGTHS AND LIMITATIONS OF THIS STUDY A retrospective study of machine learning severe sepsis prediction from a dataset with 510,497 patient encounters demonstrates high accuracy up to 48 hours prior to onset. A multicenter clinical study of real-world data using this machine learning algorithm for severe sepsis alerts achieved reductions of in-hospital mortality, length of stay, and 30-day readmissions. The required presence of an ICD-9 code to classify a patient as severely septic in our retrospective analysis potentially limits our ability to accurately classify all patients. Only adults in US hospitals were included in this study. For the real-world section of the study, we cannot eliminate the possibility that implementation of a sepsis algorithm raised general awareness of sepsis within a hospital, which may lead to higher recognition of septic patients, independent of algorithm performance. 93.1% topic match

93.1%

0.8

2021

[151] Modelling and Classification of Sepsis using Machine Learning I. Amrita, ..., and K. Ashwini 2021 5th International Conference on Electrical, Electronics, Communication, Computer Technologies and Optimization Techniques (ICEECCOT) 2021 - 2 citations - Show abstract - Cite 93.1% topic match

93.1%

0.2

2020

[152] Sepsis Prediction using Continuous and Categorical Features on Sporadic Data Varsha Sharma, ..., and A. Choudhury 2020 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops) 2020 - 1 citations - Show abstract - Cite 93.1% topic match

93.1%

2.1

2020

[153] AI in the Intensive Care Unit: Up-to-Date Review Diep Nguyen, ..., and E. vanSonnenberg Journal of Intensive Care Medicine 2020 - 8 citations - Show abstract - Cite 93.1% topic match

93.1%

15.4

2017

[154] Reducing patient mortality, length of stay and readmissions through machine learning-based sepsis prediction in the emergency department, intensive care unit and hospital floor units Andrea McCoy and R. Das BMJ Open Quality 2017 - 105 citations - Show abstract - Cite 93.1% topic match

93.0%

1.4

2019

[155] An Ensemble of Bagged Decision Trees for Early Prediction of Sepsis Reza Firoozabadi and S. Babaeizadeh 2019 Computing in Cardiology (CinC) 2019 - 7 citations - Show abstract - Cite 93.0% topic match

93.0%

1.0

2021

[156] Recurrent Neural Networks for Early Detection of Late Onset Sepsis in Premature Infants Using Heart Rate Variability Cristhyne León, ..., and G. Carrault 2021 Computing in Cardiology (CinC) 2021 - 3 citations - Show abstract - Cite 93.0% topic match

92.9%

1.1

2021

[157] Unsupervised learning approach for predicting sepsis onset in ICU patients Guilherme Ramos, ..., and M. Silveira 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) 2021 - 3 citations - Show abstract - Cite 92.9% topic match

92.6%

0.0

2023

[158] Early prediction of mortality at sepsis diagnosis time in critically ill patients by using interpretable machine learning. Yi-Wei Cheng, ..., and Yu-Chang Yeh Journal of clinical monitoring and computing 2023 - 0 citations - Show abstract - Cite 92.6% topic match

92.6%

0.0

2022

[159] [Research progress on application of artificial intelligence in early diagnosis and prediction of sepsis]. Qimei Wei and Guanghui Xiu Zhonghua wei zhong bing ji jiu yi xue 2022 - 0 citations - Show abstract - Cite 92.6% topic match

Reviews AI in early sepsis diagnosis and prediction. Highlights AI's potential in improving prognosis through rapid data processing and analysis. Discusses the limitations and importance of AI in sepsis diagnosis in critical care.

Reviews AI in early sepsis diagnosis and prediction. Highlights AI's potential in improving prognosis through rapid data processing and analysis. Discusses the limitations and importance of AI in sepsis diagnosis in critical care.

92.6%

2.1

2022

[160] A Machine Learning-Enabled Partially Observable Markov Decision Process Framework for Early Sepsis Prediction Zeyu Liu, ..., and Rishikesan Kamaleswaran INFORMS J. Comput. 2022 - 5 citations - Show abstract - Cite Abstract: Sepsis is a life-threatening condition, caused by the body’s extreme response to an infection. In the United States, 1.7 million cases of sepsis occur annually, resulting in 265,000 deaths. Delayed diagnosis and treatment are associated with higher mortality rates. An exponential rise in the availability of medical data has allowed for the development of sophisticated machine learning algorithms to predict sepsis earlier than the onset. However, these models often underperform, as the training data are retrospective and do not fully capture the uncertain future. In this study, we develop a novel framework, which we refer to as MLePOMDP, to leverage and combine the underlying, high-level knowledge about sepsis progression and machine learning (ML) for classification. Specifically, we use a hidden Markov model to describe sepsis development at a high level, where the ML model makes the higher-order “observations” from temporal data. Consequently, a partially observable Markov decision process (POMDP) model is developed to make classification decisions. We analytically establish that the optimal policy is of threshold-type, which we exploit to efficiently optimize MLePOMDP. MLePOMDP is calibrated and tested using high-frequency physiological data collected from bedside monitors. Different from past POMDP-based frameworks, MLePOMDP is developed for a prediction task using a very small state definition, produces highly interpretable results, and accounts for a novel and clinically meaningful action space. Our results show that MLePOMDP outperforms machine learning–based benchmarks by up to 8% in precision. Importantly, MLePOMDP is able to reduce false alarms by up to 28%. An additional experiment is conducted to show the generalizability of MLePOMDP to different patient cohorts. Summary of Contribution: This study develops a novel real-time decision support framework for early sepsis prediction by integrating well-known machine learning models (random forest and neural networks) with a well-established sequential decision-making model, namely, a partially observable Markov decision process (POMDP). The structural properties of the optimal policy are further explored and a threshold-type structure is established, which is then leveraged to develop a customized algorithm to solve the problem more efficiently. The resulting framework demonstrates the benefit of applying POMDPs to augment machine learning outputs. Specifically, the framework results in the reduction of false alarms in sepsis predictions where decisions are made in real time, hence improving the overall prediction precision. 92.6% topic match

92.6%

1.2

2023

[161] The application of artificial intelligence in the management of sepsis Jie Yang, ..., and Zhongheng Zhang Medical Review 2023 - 1 citations - Show abstract - Cite 92.6% topic match

Reviews AI's evolving role in sepsis management. Focuses on early detection, precise treatment, and prognosis in ICU patients using AI. Highlights AI-driven early warning systems for enhanced sepsis intervention.

Reviews AI's evolving role in sepsis management. Focuses on early detection, precise treatment, and prognosis in ICU patients using AI. Highlights AI-driven early warning systems for enhanced sepsis intervention.

92.6%

0.4

2022

[162] Artificial Intelligence for the Prediction of Sepsis in Adults R. Haas and Sarah C. McGill Canadian Journal of Health Technologies 2022 - 1 citations - Show abstract - Cite 92.6% topic match

92.6%

0.0

2019

[163] Early Sepsis Detection with Deep Learning on EHR Event Sequences S. Lauritsen, ..., and B. Thiesson Dansk Tidsskrift for Akutmedicin 2019 - 0 citations - Show abstract - Cite Abstract: Background: Sepsis is a clinical condition involving an extreme inflammatory response to an infection, and is associated with high morbidity and mortality. Without intervention, this response can progress to septic shock, organ failure and death. Every hour that treatment is delayed mortality increases. Early identification of sepsis is therefore important for a positive outcome. Methods: We constructed predictive models for sepsis detection and performed a register-based cohort study on patients from four Danish municipalities. We used event-sequences of raw electronic health record (EHR) data from 2013 to 2017, where each event consists of three elements: a timestamp, an event category (e.g. medication code), and a value. In total, we consider 25.622 positive (SIRS criteria) sequences and 25.622 negative sequences with a total of 112 million events distributed across 64 different hospital units. The number of potential predictor variables in raw EHR data easily exceeds 10.000 and can be challenging for predictive modeling due to this large volume of sparse, heterogeneous events. Traditional approaches have dealt with this complexity by curating a limited number of variables of importance; a labor-intensive process that may discard a vast majority of information. In contrast, we consider a deep learning system constructed as a combination of a convolutional neural network (CNN) and long short-term memory (LSTM) network. Importantly, our system learns representations of the key factors and interactions from the raw event sequence data itself. Results: Our model predicts sepsis with an AUROC score of 0.8678, at 11 hours before actual treatment was started, outperforming all currently deployed approaches. At other prediction times, the model yields following AUROC scores. 15 min: 0.9058, 3 hours: 0.8803, 24 hours: 0.8073. Conclusion: We have presented a novel approach for early detection of sepsis that has more true positives and fewer false negatives than existing alarm systems without introducing domain knowledge into the model. Importantly, the model does not require changes in the daily workflow of healthcare professionals at hospitals, as the model is based on data that is routinely captured in the EHR. This also enables real-time prediction, as healthcare professionals enters the raw events in the EHR. 92.6% topic match

92.5%

0.0

2023

[164] Mortality prediction of patients with sepsis in the emergency department using machine learning models: a retrospective cohort study according to the Sepsis-3 definitions No author found Signa Vitae 2023 - 0 citations - Show abstract - Cite 92.5% topic match

92.5%

2.4

2019

[165] An Ensemble Machine Learning Model For the Early Detection of Sepsis From Clinical Data Mengsha Fu, ..., and M. Zeng 2019 Computing in Cardiology (CinC) 2019 - 12 citations - Show abstract - Cite 92.5% topic match

92.5%

4.5

2017

[166] LSTM for septic shock: Adding unreliable labels to reliable predictions Yuan Zhang, ..., and J. Huddleston 2017 IEEE International Conference on Big Data (Big Data) 2017 - 30 citations - Show abstract - Cite 92.5% topic match

92.4%

33.4

2017

[167] Effect of a machine learning-based severe sepsis prediction algorithm on patient survival and hospital length of stay: a randomised clinical trial David Shimabukuro, ..., and R. Das BMJ Open Respiratory Research 2017 - 225 citations - Show abstract - Cite Abstract: Introduction Several methods have been developed to electronically monitor patients for severe sepsis, but few provide predictive capabilities to enable early intervention; furthermore, no severe sepsis prediction systems have been previously validated in a randomised study. We tested the use of a machine learning-based severe sepsis prediction system for reductions in average length of stay and in-hospital mortality rate. Methods We conducted a randomised controlled clinical trial at two medical-surgical intensive care units at the University of California, San Francisco Medical Center, evaluating the primary outcome of average length of stay, and secondary outcome of in-hospital mortality rate from December 2016 to February 2017. Adult patients (18+) admitted to participating units were eligible for this factorial, open-label study. Enrolled patients were assigned to a trial arm by a random allocation sequence. In the control group, only the current severe sepsis detector was used; in the experimental group, the machine learning algorithm (MLA) was also used. On receiving an alert, the care team evaluated the patient and initiated the severe sepsis bundle, if appropriate. Although participants were randomly assigned to a trial arm, group assignments were automatically revealed for any patients who received MLA alerts. Results Outcomes from 75 patients in the control and 67 patients in the experimental group were analysed. Average length of stay decreased from 13.0 days in the control to 10.3 days in the experimental group (p=0.042). In-hospital mortality decreased by 12.4 percentage points when using the MLA (p=0.018), a relative reduction of 58.0%. No adverse events were reported during this trial. Conclusion The MLA was associated with improved patient outcomes. This is the first randomised controlled trial of a sepsis surveillance system to demonstrate statistically significant differences in length of stay and in-hospital mortality. Trial registration NCT03015454. 92.4% topic match

92.3%

3.7

2020

[168] Two-Stage Monitoring of Patients in Intensive Care Unit for Sepsis Prediction Using Non-Overfitted Machine Learning Models Vytautas Abromavičius, ..., and A. Serackis Electronics 2020 - 15 citations - Show abstract - Cite 92.3% topic match

92.3%

0.0

2023

[169] Artificial Intelligence Based Early Diagnosis of Sepsis Amer Kareem, ..., and P. Sasikala 2023 3rd International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE) 2023 - 0 citations - Show abstract - Cite 92.3% topic match

Summarizes AI's role in early sepsis diagnosis in ICU. Outlines AI's potential in predicting, prognostication, and treatment decisions for sepsis. Discusses implementation challenges of AI in clinical sepsis management.

Summarizes AI's role in early sepsis diagnosis in ICU. Outlines AI's potential in predicting, prognostication, and treatment decisions for sepsis. Discusses implementation challenges of AI in clinical sepsis management.

92.2%

3.4

2019

[170] Natural Language Processing of Clinical Notes for Improved Early Prediction of Septic Shock in the ICU Ran Liu, ..., and R. Winslow 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) 2019 - 17 citations - Show abstract - Cite 92.2% topic match

92.2%

12.4

2018

[171] Improving Sepsis Treatment Strategies by Combining Deep and Kernel-Based Reinforcement Learning Xuefeng Peng, ..., and F. Doshi-Velez AMIA ... Annual Symposium proceedings. AMIA Symposium 2018 - 70 citations - Show abstract - Cite - PDF 92.2% topic match

92.1%

3.5

2023

[172] Rethinking Human-AI Collaboration in Complex Medical Decision Making: A Case Study in Sepsis Diagnosis Shao Zhang, ..., and Dakuo Wang ArXiv 2023 - 3 citations - Show abstract - Cite - PDF 92.1% topic match

92.1%

2.9

2021

[173] Machine Learning Model to Identify Sepsis Patients in the Emergency Department: Algorithm Development and Validation Pei-Chen Lin, ..., and Ming-Chin Lin Journal of Personalized Medicine 2021 - 8 citations - Show abstract - Cite Abstract: Accurate stratification of sepsis can effectively guide the triage of patient care and shared decision making in the emergency department (ED). However, previous research on sepsis identification models focused mainly on ICU patients, and discrepancies in model performance between the development and external validation datasets are rarely evaluated. The aim of our study was to develop and externally validate a machine learning model to stratify sepsis patients in the ED. We retrospectively collected clinical data from two geographically separate institutes that provided a different level of care at different time periods. The Sepsis-3 criteria were used as the reference standard in both datasets for identifying true sepsis cases. An eXtreme Gradient Boosting (XGBoost) algorithm was developed to stratify sepsis patients and the performance of the model was compared with traditional clinical sepsis tools; quick Sequential Organ Failure Assessment (qSOFA) and Systemic Inflammatory Response Syndrome (SIRS). There were 8296 patients (1752 (21%) being septic) in the development and 1744 patients (506 (29%) being septic) in the external validation datasets. The mortality of septic patients in the development and validation datasets was 13.5% and 17%, respectively. In the internal validation, XGBoost achieved an area under the receiver operating characteristic curve (AUROC) of 0.86, exceeding SIRS (0.68) and qSOFA (0.56). The performance of XGBoost deteriorated in the external validation (the AUROC of XGBoost, SIRS and qSOFA was 0.75, 0.57 and 0.66, respectively). Heterogeneity in patient characteristics, such as sepsis prevalence, severity, age, comorbidity and infection focus, could reduce model performance. Our model showed good discriminative capabilities for the identification of sepsis patients and outperformed the existing sepsis identification tools. Implementation of the ML model in the ED can facilitate timely sepsis identification and treatment. However, dataset discrepancies should be carefully evaluated before implementing the ML approach in clinical practice. This finding reinforces the necessity for future studies to perform external validation to ensure the generalisability of any developed ML approaches. 92.1% topic match

92.1%

0.2

2019

[174] Sepsis Prediction Model Based on Vital Signs Related Features Vytautas Abromavičius and A. Serackis 2019 Computing in Cardiology (CinC) 2019 - 1 citations - Show abstract - Cite 92.1% topic match

92.0%

1.0

2021

[175] SepINav (Sepsis ICU Navigator): A data-driven software tool for sepsis monitoring and intervention using Bayesian Online Change Point Detection N. Sakib, ..., and Sheikh Iqbal Ahamed SoftwareX 2021 - 3 citations - Show abstract - Cite 92.0% topic match

92.0%

0.6

2019

[176] Early Sepsis Prediction in ICU Trauma Patients with Using An Improved Cascade Deep Forest Model Mengsha Fu, ..., and Chen Bei 2019 IEEE 10th International Conference on Software Engineering and Service Science (ICSESS) 2019 - 3 citations - Show abstract - Cite 92.0% topic match

91.9%

9.4

2018

[177] A New Effective Machine Learning Framework for Sepsis Diagnosis Xianchuan Wang, ..., and Xianqin Wang IEEE Access 2018 - 62 citations - Show abstract - Cite 91.9% topic match

91.9%

0.0

2022

[178] Development and Validation of an Explainable Deep Learning Model to Predict Adverse Event During Hospital Admission in Patients with Sepsis I-Min Chiu, ..., and C. Lin 2022 IEEE/ACIS 23rd International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD) 2022 - 0 citations - Show abstract - Cite 91.9% topic match

91.8%

2.3

2023

[179] Real-Time Prediction of Sepsis in Critical Trauma Patients: Machine Learning–Based Modeling Study Jiang Li, ..., and Xiling Wang JMIR Formative Research 2023 - 3 citations - Show abstract - Cite Abstract: Background Sepsis is a leading cause of death in patients with trauma, and the risk of mortality increases significantly for each hour of delay in treatment. A hypermetabolic baseline and explosive inflammatory immune response mask clinical signs and symptoms of sepsis in trauma patients, making early diagnosis of sepsis more challenging. Machine learning–based predictive modeling has shown great promise in evaluating and predicting sepsis risk in the general intensive care unit (ICU) setting, but there has been no sepsis prediction model specifically developed for trauma patients so far. Objective To develop a machine learning model to predict the risk of sepsis at an hourly scale among ICU-admitted trauma patients. Methods We extracted data from adult trauma patients admitted to the ICU at Beth Israel Deaconess Medical Center between 2008 and 2019. A total of 42 raw variables were collected, including demographics, vital signs, arterial blood gas, and laboratory tests. We further derived a total of 485 features, including measurement pattern features, scoring features, and time-series variables, from the raw variables by feature engineering. The data set was randomly split into 70% for model development with stratified 5-fold cross-validation, 15% for calibration, and 15% for testing. An Extreme Gradient Boosting (XGBoost) model was developed to predict the hourly risk of sepsis at prediction windows of 4, 6, 8, 12, and 24 hours. We evaluated model performance for discrimination and calibration both at time-step and outcome levels. Clinical applicability of the model was evaluated with varying levels of precision, and the potential clinical net benefit was assessed with decision curve analysis (DCA). A Shapley additive explanation algorithm was applied to show the effect of features on the prediction model. In addition, we trained an L2-regularized logistic regression model to compare its performance with XGBoost. Results We included 4603 trauma patients in the study, 1196 (26%) of whom developed sepsis. The XGBoost model achieved an area under the receiver operating characteristics curve (AUROC) ranging from 0.83 to 0.88 at the 4-to-24-hour prediction window in the test set. With a ratio of 9 false alerts for every true alert, it predicted 73% (386/529) of sepsis-positive timesteps and 91% (163/179) of sepsis events in the subsequent 6 hours. The DCA showed our model had a positive net benefit in the threshold probability range of 0 to 0.6. In comparison, the logistic regression model achieved lower performance, with AUROC ranging from 0.76 to 0.84 at the 4-to-24-hour prediction window. Conclusions The machine learning–based model had good discrimination and calibration performance for sepsis prediction in critical trauma patients. Using the model in clinical practice might help to identify patients at risk of sepsis in a time window that enables personalized intervention and early treatment. 91.8% topic match

91.8%

5.6

2021

[180] Artificial Intelligence for Clinical Decision Support in Sepsis Miao Wu, ..., and Jie Wei Frontiers in Medicine 2021 - 18 citations - Show abstract - Cite 91.8% topic match

Reviews AI in clinical decision support for sepsis. Discusses AI's role in early prediction, diagnosis, and prognosis of sepsis. Highlights implementation challenges of AI in clinical settings.

Reviews AI in clinical decision support for sepsis. Discusses AI's role in early prediction, diagnosis, and prognosis of sepsis. Highlights implementation challenges of AI in clinical settings.

91.7%

2.0

2019

[181] A Recurrent Neural Network for the Prediction of Vital Sign Evolution and Sepsis in ICU Benjamin Roussel, ..., and J. Oster 2019 Computing in Cardiology (CinC) 2019 - 10 citations - Show abstract - Cite 91.7% topic match

91.7%

2.9

2019

[182] Early Prediction of Sepsis Using Random Forest Classification for Imbalanced Clinical Data Simon Lyra, ..., and C. H. Antink 2019 Computing in Cardiology (CinC) 2019 - 14 citations - Show abstract - Cite 91.7% topic match

91.6%

0.0

2023

[183] AI Based Smart Intensive Care Unit – A Survey Sharmila S, ..., and Harihareshwer R 2023 International Conference on Intelligent Technologies for Sustainable Electric and Communications Systems (iTech SECOM) 2023 - 0 citations - Show abstract - Cite 91.6% topic match

91.5%

0.4

2021

[184] Predicting the Risk of Death for Sepsis Based on Within-Class Mixup and Lightgbm Xun Wang, ..., and Yulong Hao Proceedings of the 2021 4th International Conference on Artificial Intelligence and Pattern Recognition 2021 - 1 citations - Show abstract - Cite 91.5% topic match

91.5%

3.5

2022

[185] Diagnostic performance of machine learning models using cell population data for the detection of sepsis: a comparative study U. Aguirre and E. Urrechaga Clinical Chemistry and Laboratory Medicine (CCLM) 2022 - 6 citations - Show abstract - Cite 91.5% topic match

91.5%

0.3

2021

[186] Sepsis Detection Using Extreme Gradient Boost (XGB): A Supervised Learning Approach Asad Ullah, ..., and Fawad Ahmad 2021 Mohammad Ali Jinnah University International Conference on Computing (MAJICC) 2021 - 1 citations - Show abstract - Cite 91.5% topic match

91.5%

6.2

2019

[187] Improving Prediction Performance Using Hierarchical Analysis of Real-Time Data: A Sepsis Case Study F. van Wyk, ..., and Rishikesan Kamaleswaran IEEE Journal of Biomedical and Health Informatics 2019 - 34 citations - Show abstract - Cite 91.5% topic match

91.4%

0.9

2023

[188] PT3: A Transformer-based Model for Sepsis Death Risk Prediction via Vital Signs Time Series R. Luo, ..., and Chunping Li 2023 International Joint Conference on Neural Networks (IJCNN) 2023 - 1 citations - Show abstract - Cite 91.4% topic match

91.3%

0.0

2023

[189] Comparison of Machine Learning Models for Predictive Analytics of Sepsis in the Emergency Medical Admissions Vandana and Parli B. Hari 2023 5th International Conference on Inventive Research in Computing Applications (ICIRCA) 2023 - 0 citations - Show abstract - Cite Abstract: Sepsis is a blood poisoning condition which can increase the mortality rate for ICU patients. The expense of treating sepsis in hospitals is rising every year as it becomes a serious health issue. Different techniques have been established to monitor sepsis, but it is essential to predict sepsis as early as possible because treatment delays can raise the risk of fatalities every hour. Artificial Intelligence and Machine Learning have made enormous strides recently, and this has greatly impacted the medical industry. Sepsis may be predicted in advance using machine learning algorithms, which aids in helping patients get the right treatment as soon as possible. The dataset used in this research study was obtained from the Physionet website and used to compare several Machine Learning methods. A combination of Last Observation Carry forward (LOCF) and Next Observation Carried Backwards (NOCB) was carried out to handle missing data for each patient. Another major concern in the data is that it is highly imbalanced. 98% of the data belongs to non-Sepsis category as per Sepsis-3 criteria. It is difficult to train machine learning models with a large number of unbalanced data. Thus, this situation is unsuitable for training traditional classifiers. For handling large imbalanced data, a combination of SmoteTomek and NearMiss techniques is used, which is a new initiative. SmoteTomek is the combination of under sampling and over sampling. NearMiss is under sampling technique. After applying these techniques, balanced data is obtained, which is a necessity for most of the classification machine learning algorithms. Various classification machine learning algorithms have been implemented for predictive analytics. This research study compares various algorithmic parameters like auroc, recall, f1 measure, accuracy, error rate and others. After comparative analysis of machine learning models, Random Forest model has achieved highest auroc as 0.996, specificity as 0.998, accuracy as 0.994, f measure as 0.855 and error rate as 0.006, recall as 0.811. KNN model showed maximum sensitivity of 0.922, with auroc as 0.972, accuracy as 0.984, f measure as 0.718 and error rate as 0.016. It showed more sensitivity and specificity as compared to Epic Sepsis Model(ESM). So, it is recommended for conducting clinical assessment of a patient with Sepsis. 91.3% topic match

Compares AI models for early sepsis prediction in emergency admissions. Utilizes Physionet's dataset to examine the effectiveness of different Machine Learning techniques. Focuses on emergency medical admissions rather than exclusive ICU patient scenarios.

Compares AI models for early sepsis prediction in emergency admissions. Utilizes Physionet's dataset to examine the effectiveness of different Machine Learning techniques. Focuses on emergency medical admissions rather than exclusive ICU patient scenarios.

91.3%

3.2

2021

[190] Deep Multi-Modal Transfer Learning for Augmented Patient Acuity Assessment in the Intelligent ICU B. Shickel, ..., and Parisa Rashidi Frontiers in Digital Health 2021 - 11 citations - Show abstract - Cite 91.3% topic match

91.3%

1.7

2022

[191] Machine learning models for predicting in-hospital mortality in patient with sepsis: Analysis of vital sign dynamics Chi-Yung Cheng, ..., and Chih-Min Su Frontiers in Medicine 2022 - 3 citations - Show abstract - Cite 91.3% topic match

90.9%

10.2

2019

[192] A minimal set of physiomarkers in continuous high frequency data streams predict adult sepsis onset earlier F. V. Wyk, ..., and Rishikesan Kamaleswaran International journal of medical informatics 2019 - 56 citations - Show abstract - Cite 90.9% topic match

90.9%

0.3

2020

[193] Voting of predictive models for clinical outcomes: consensus of algorithms for the early prediction of sepsis from clinical data and an analysis of the PhysioNet/Computing in Cardiology Challenge 2019 M. Reyna and G. Clifford ArXiv 2020 - 1 citations - Show abstract - Cite - PDF 90.9% topic match

90.9%

0.0

2022

[194] Applying Machine Learning to Blood Count Data Predicts Sepsis with ICU Admission Paul C. Ahrens, ..., and Thorsten Kaiser medRxiv 2022 - 0 citations - Show abstract - Cite Abstract: Background: Delay in diagnosing sepsis results in potentially preventable deaths. Mainly due to their complexity or limited applicability, machine learning (ML) models to predict sepsis have not yet become part of clinical routines. For this reason, we created a ML model that only requires complete blood count (CBC) diagnostics. Methods: Non-intensive care unit (non-ICU) data from a German tertiary care centre were collected from January 2014 to December 2021. Patient age, sex, and CBC parameters (haemoglobin, platelets, mean corpuscular volume, white and red blood cells) were utilised to train a boosted random forest, which predicts sepsis with ICU admission. Two external validations were conducted using data from another German tertiary care centre and the Medical Information Mart for Intensive Care IV database (MIMIC-IV). Using the subset of laboratory orders also including procalcitonin (PCT), an analogous model was trained with PCT as an additional feature. Findings: After exclusion, 1,381,358 laboratory requests (2016 from sepsis cases) were available. The derived CBC model shows an area under the receiver operating characteristic (AUROC) of 0.872 (95% CI, 0.857-0.887) for predicting sepsis. External validations show AUROCs of 0.805 (95% CI, 0.787-0.824) and 0.845 (95% CI, 0.837-0.852) for MIMIC-IV. The model including PCT revealed a significantly higher performance (AUROC: 0.857; 95% CI, 0.836-0.877) than PCT alone (AUROC: 0.790; 95% CI, 0.759-0.821; p<0.001). Interpretation: Our results demonstrate that routine CBC results could significantly improve diagnosis of sepsis when combined with ML. The CBC model can facilitate early sepsis prediction in non-ICU patients with high robustness in external validations. Its implementation in clinical decision support systems has strong potential to provide an essential time advantage and increase patient safety. Funding: The study was part of the AMPEL project (www.ampel.care), which is co-financed through public funds according to the budget decided by the Saxon State Parliament under the RL eHealthSax 2017/18 grant number 100331796. 90.9% topic match

90.7%

0.4

2016

[195] Using demographic and time series physiological features to classify sepsis in the intensive care unit. K. Gunnarsdottir, ..., and S. Sarma Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference 2016 - 3 citations - Show abstract - Cite 90.7% topic match

90.7%

0.5

2020

[196] Early Predicton of Sepsis using Clinical Data R. Lakshmi Devi, ..., and Ponsubashini B 2020 International Conference on System, Computation, Automation and Networking (ICSCAN) 2020 - 2 citations - Show abstract - Cite 90.7% topic match

90.7%

2.3

2023

[197] Dynamic Prediction of Patient Outcomes in the Intensive Care Unit: A Scoping Review of the State-of-the-Art L. Lapp, ..., and S. Schraag Journal of Intensive Care Medicine 2023 - 3 citations - Show abstract - Cite Abstract: Introduction Intensive care units (ICUs) are high-pressure, complex, technology-intensive medical environments where patient physiological data are generated continuously. Due to the complexity of interpreting multiple signals at speed, there are substantial opportunities and significant potential benefits in providing ICU staff with additional decision support and predictive modeling tools that can support and aid decision-making in real-time. This scoping review aims to synthesize the state-of-the-art dynamic prediction models of patient outcomes developed for use in the ICU. We define “dynamic” models as those where predictions are regularly computed and updated over time in response to updated physiological signals. Methods Studies describing the development of predictive models for use in the ICU were searched, using PubMed. The studies were screened as per Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) guidelines, and the data regarding predicted outcomes, methods used to develop the predictive models, preprocessing the data and dealing with missing values, and performance measures were extracted and analyzed. Results A total of n = 36 studies were included for synthesis in our review. The included studies focused on the prediction of various outcomes, including mortality (n = 17), sepsis-related complications (n = 12), cardiovascular complications (n = 5), and other complications (respiratory, renal complications, and bleeding, n = 5). The most common classification methods include logistic regression, random forest, support vector machine, and neural networks. Conclusion The included studies demonstrated that there is a strong interest in developing dynamic prediction models for various ICU patient outcomes. Most models reported focus on mortality. As such, the development of further models focusing on a range of other serious and well-defined complications—such as acute kidney injury—would be beneficial. Furthermore, studies should improve the reporting of key aspects of model development challenges. 90.7% topic match

90.7%

0.7

2019

[198] Early Detection of Sepsis in ICU Patients Using Logistic Regression Fahim Mahmud, ..., and M. Quamruzzaman 2019 3rd International Conference on Electrical, Computer & Telecommunication Engineering (ICECTE) 2019 - 3 citations - Show abstract - Cite 90.7% topic match

90.6%

0.6

2019

[199] Prediction of Sepsis from Clinical Data Using Long Short-Term Memory and eXtreme Gradient Boosting Yongchao Wang, ..., and Xu Ma 2019 Computing in Cardiology (CinC) 2019 - 3 citations - Show abstract - Cite 90.6% topic match

90.6%

11.6

2020

[200] Effect of a sepsis prediction algorithm on patient mortality, length of stay and readmission: a prospective multicentre clinical outcomes evaluation of real-world patient data from US hospitals Hoyt J Burdick, ..., and R. Das BMJ Health & Care Informatics 2020 - 50 citations - Show abstract - Cite 90.6% topic match

90.5%

0.4

2019

[201] Influencing outcomes with automated time zero for sepsis through statistical validation and process improvement. Karen Colorafi, ..., and Joseph Colorafi mHealth 2019 - 2 citations - Show abstract - Cite 90.5% topic match

90.5%

1.2

2022

[202] Intelligent Clinical Decision Support M. Pinsky, ..., and G. Clermont Sensors (Basel, Switzerland) 2022 - 3 citations - Show abstract - Cite 90.5% topic match

90.4%

0.2

2019

[203] INTENSIVE CARE UNIT ( ICU ) DATA ANALYTICS USING MACHINE LEARNING TECHNIQUES Zeina Rayan, ..., and Abdel-badeeh M. Salem Journal Not Provided 2019 - 1 citations - Show abstract - Cite 90.4% topic match

90.2%

1.6

2019

[204] Sepsis Detection in Sparse Clinical Data Using Long Short-Term Memory Network with Dice Loss Tomáš Vičar, ..., and R. Smíšek 2019 Computing in Cardiology (CinC) 2019 - 8 citations - Show abstract - Cite 90.2% topic match

90.1%

0.2

2019

[205] An Algorithm for Early Detection of Sepsis Using Traditional Statistical Regression Modeling Roshan Pawar, ..., and M. Görges 2019 Computing in Cardiology (CinC) 2019 - 1 citations - Show abstract - Cite 90.1% topic match

89.9%

0.0

2023

[206] Deep Attention Q-Network for Personalized Treatment Recommendation Simin Ma, ..., and Shihao Yang 2023 IEEE International Conference on Data Mining Workshops (ICDMW) 2023 - 0 citations - Show abstract - Cite - PDF 89.9% topic match

89.8%

0.0

2023

[207] Early Prediction of Sepsis using ML Algorithms on Clinical Data Smitha N, ..., and V. K R 2023 14th International Conference on Computing Communication and Networking Technologies (ICCCNT) 2023 - 0 citations - Show abstract - Cite 89.8% topic match

89.7%

4.6

2008

[208] Presymptomatic Prediction of Sepsis in Intensive Care Unit Patients R. Lukaszewski, ..., and Michael J. Pearce Clinical and Vaccine Immunology 2008 - 74 citations - Show abstract - Cite 89.7% topic match

89.7%

0.0

2020

[209] Is AI in Healthcare Doomed, or Destined for Greatness? B. Elahi Journal of System Safety 2020 - 0 citations - Show abstract - Cite 89.7% topic match

89.5%

0.2

2019

[210] Randomly Under Sampled Boosted Tree for Predicting Sepsis From Intensive Care Unit Databases Peter Doggart and M. Rutherford 2019 Computing in Cardiology (CinC) 2019 - 1 citations - Show abstract - Cite 89.5% topic match

89.5%

0.5

2019

[211] PREDICTION OF SEPSIS DISEASE BY ARTIFICIAL NEURAL NETWORKS Umut Kaya, ..., and Y. Dikmen Journal Not Provided 2019 - 3 citations - Show abstract - Cite 89.5% topic match

89.3%

0.0

2021

[212] A Comparative Study of Machine Learning Techniques for Predicting Sepsis for MIMIC-III Patients Xuze Zhao and Bo Qu https://doi.org/10.21203/RS.3.RS-697902/V1 2021 - 0 citations - Show abstract - Cite 89.3% topic match

89.3%

0.7

2023

[213] Application of artificial intelligence techniques in the intensive care unit Prabhudutta Ray, ..., and R. Raval International Journal of Reconfigurable and Embedded Systems (IJRES) 2023 - 1 citations - Show abstract - Cite 89.3% topic match

89.3%

0.4

2022

[214] A Machine Learning Pipeline for Mortality Prediction in the ICU Y. Sun and Yi‐Hui Zhou International Journal of Digital Health 2022 - 1 citations - Show abstract - Cite 89.3% topic match

89.2%

0.3

2021

[215] An Application of Predictive Analytics for Early Detection of Sepsis: An Overview Anjali Kshirsagar, ..., and Prof. Sushma Vispute Journal Not Provided 2021 - 1 citations - Show abstract - Cite 89.2% topic match

89.2%

0.0

2022

[216] World Journal of Critical Care Medicine No author found Journal Not Provided 2022 - 0 citations - Show abstract - Cite 89.2% topic match

89.2%

0.0

2020

[217] IMPROVING PREDICTION PERFORMANCE FOR SEPSIS USING RANDOM FOREST APPROACH K. Parameshwari and V. Sasireka https://doi.org/10.23883/ijrter.2020.6019.thqqe 2020 - 0 citations - Show abstract - Cite 89.2% topic match

89.1%

0.0

2020

[218] A machine-learning approach for dynamic prediction of sepsis-induced coagulopathy in critically ill patients with sepsis: an integrated analysis of the MIMIC-IV and eICU-CRD databases Qin-yu Zhao, ..., and Zhe Luo https://doi.org/10.21203/rs.3.rs-125438/v1 2020 - 0 citations - Show abstract - Cite Abstract: Background Sepsis-induced coagulopathy (SIC) denotes an increased mortality rate and poorer prognosis in septic patients. Methods Machine-learning models were developed based on septic patients who were older than 18 years and stayed in intensive care units (ICUs) for more than 24 hours in Medical Information Mart for Intensive Care (MIMIC)-IV. Eighty-eight potential predictors were extracted, and 15 various machine-learning models assessed the daily risk of SIC. The most potent model was selected based on its accuracy and Area Under the receiver operating characteristic Curve (AUC), followed by fine-grained hyperparameter adjustment using the Bayesian Optimization Algorithm. The effects of features on prediction scores were measured using the SHapley Additive exPlanations (SHAP) values. A compact model was developed, based on 15 features selected according to their importance and clinical availability. Two models were compared with Logistic Regression and SIC scores in terms of SIC prediction. Additionally, an external validation was performed in the eICU Collaborative Research Database (eICU-CRD). Results Of 11362 patients in MIMIC-IV included in the final cohort, a total of 6744 (59%) patients had SIC during sepsis, and 16183 samples were extracted. The model named Categorical Boosting (CatBoost) had the greatest AUC in our study (0.869 [0.850, 0.886]). Coagulation profile and renal function indicators are the most important features to predict SIC. A compact model was developed with the AUC of 0.854 [0.832, 0.872], while the AUCs of Logistic Regression and SIC scores were 0.746 [0.735, 0.755] and 0.709 [0.687, 0.733], respectively. A cohort of 35252 septic patients in eICU-CRD was analyzed. The AUCs of the full and the compact models in external validation were 0.842 [0.837, 0.846] and 0.803 [0.798, 0.809], respectively, which were still larger than those of Logistic Regression (0.660 [0.653, 0.667]) and SIC scores (0.752 [0.747, 0.757]). Prediction results can be illustrated by using SHAP values in the instance level, which makes our models clinically interpretable. Conclusions We developed two models which were able to dynamically predict the risk of SIC in septic patients better than conventional Logistic Regression and SIC scores. Prediction results of our two models can be interpreted by using SHAP values. 89.1% topic match

89.1%

1.3

2023

[219] Deep Learning in Early Prediction of Sepsis and Diagnosis Saroja Kumar Rout, ..., and Venkatesh Kavididevi 2023 International Conference for Advancement in Technology (ICONAT) 2023 - 2 citations - Show abstract - Cite 89.1% topic match

89.0%

1.6

2023

[220] An interpretable machine learning model for real-time sepsis prediction based on basic physiological indicators. T-Y Zhang, ..., and MD Mingwei Zhang European review for medical and pharmacological sciences 2023 - 2 citations - Show abstract - Cite 89.0% topic match

89.0%

0.0

2020

[221] Potential Prognostic Markers in the Heart Rate Variability Features for Early Diagnosis of Sepsis in the Pediatric Intensive Care Unit using Convolutional Neural Network Classifiers P. Amiri, ..., and M. Mirzaaghayan 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) 2020 - 0 citations - Show abstract - Cite 89.0% topic match

88.8%

1.2

2022

[222] A XGBOOST Based Algorithm for Early Prediction of Human Sepsis Karthigha M and V. Akshaya 2022 4th International Conference on Smart Systems and Inventive Technology (ICSSIT) 2022 - 3 citations - Show abstract - Cite 88.8% topic match

88.8%

None

[223] The application of arti ﬁ cial intelligence in the management of sepsis Jie Yang, ..., and Zhongheng Zhang Journal Not Provided None - 0 citations - Show abstract - Cite 88.8% topic match

88.6%

0.6

2023

[224] Exploring the potentials and challenges of Artificial Intelligence in supporting clinical diagnostics and remote assistance for the health and well-being of individuals Andrea Berti, ..., and Sara Colantonio Journal Not Provided 2023 - 1 citations - Show abstract - Cite 88.6% topic match

88.2%

1.5

2018

[225] A FHIR-Enabled Streaming Sepsis Prediction System for ICUs Joel R. Henry, ..., and S. Nemati 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) 2018 - 9 citations - Show abstract - Cite 88.2% topic match

87.5%

0.4

2019

[226] Uncertainty-Aware Model for Reliable Prediction of Sepsis in the ICU M. Pimentel, ..., and L. Tarassenko 2019 Computing in Cardiology (CinC) 2019 - 2 citations - Show abstract - Cite 87.5% topic match

87.4%

0.0

2019

[227] A Study of Early Sepsis Detection Models Based on Multivariate Medical Time Series A. Maes, ..., and D. Deschrijver Journal Not Provided 2019 - 0 citations - Show abstract - Cite 87.4% topic match

87.3%

14.4

2022

[228] Interpretable Machine Learning for Early Prediction of Prognosis in Sepsis: A Discovery and Validation Study Chang Hu, ..., and Bo Hu Infectious Diseases and Therapy 2022 - 33 citations - Show abstract - Cite 87.3% topic match

87.3%

15.4

2018

[229] Multicentre validation of a sepsis prediction algorithm using only vital sign data in the emergency department, general ward and ICU Q. Mao, ..., and R. Das BMJ Open 2018 - 101 citations - Show abstract - Cite 87.3% topic match

86.9%

0.0

2023

[230] Artificial Neural Network Application for Sepsis Prediction: A Preliminary Study AK Faizin biomej, ..., and N. A. biomej BIOMEJ 2023 - 0 citations - Show abstract - Cite 86.9% topic match

86.8%

4.6

2021

[231] Development and Validation of a Sepsis Mortality Risk Score for Sepsis-3 Patients in Intensive Care Unit Kai Zhang, ..., and Wentao Bao Frontiers in Medicine 2021 - 16 citations - Show abstract - Cite 86.8% topic match

86.7%

5.1

2020

[232] Artificial Intelligence in the Intensive Care Unit M. Greco, ..., and M. Cecconi Seminars in Respiratory and Critical Care Medicine 2020 - 19 citations - Show abstract - Cite 86.7% topic match

86.5%

0.0

2023

[233] A Predictive Model for Clinical Health Risk Using Multimodal Electronic Health Record Data Yangqiang Lin, ..., and Xichuan Zheng Proceedings of the 2023 7th International Conference on Medical and Health Informatics 2023 - 0 citations - Show abstract - Cite 86.5% topic match

86.4%

0.9

2006

[234] Predicting the risk and trajectory of intensive care patients using survival models C. W. Hug Journal Not Provided 2006 - 17 citations - Show abstract - Cite 86.4% topic match

86.4%

5.9

2020

[235] A Review of Predictive Analytics Solutions for Sepsis Patients Andrew K. Teng and A. Wilcox Applied Clinical Informatics 2020 - 25 citations - Show abstract - Cite Abstract: Abstract Background Early detection and efficient management of sepsis are important for improving health care quality, effectiveness, and costs. Due to its high cost and prevalence, sepsis is a major focus area across institutions and many studies have emerged over the past years with different models or novel machine learning techniques in early detection of sepsis or potential mortality associated with sepsis. Objective To understand predictive analytics solutions for sepsis patients, either in early detection of onset or mortality. Methods and Results We performed a systematized narrative review and identified common and unique characteristics between their approaches and results in studies that used predictive analytics solutions for sepsis patients. After reviewing 148 retrieved papers, a total of 31 qualifying papers were analyzed with variances in model, including linear regression (n = 2), logistic regression (n = 5), support vector machines (n = 4), and Markov models (n = 4), as well as population (range: 24–198,833) and feature size (range: 2–285). Many of the studies used local data sets of varying sizes and locations while others used the publicly available Medical Information Mart for Intensive Care data. Additionally, vital signs or laboratory test results were commonly used as features for training and testing purposes; however, a few used more unique features including gene expression data from blood plasma and unstructured text and data from clinician notes. Conclusion Overall, we found variation in the domain of predictive analytics tools for septic patients, from feature and population size to choice of method or algorithm. There are still limitations in transferability and generalizability of the algorithms or methods used. However, it is evident that implementing predictive analytics tools are beneficial in the early detection of sepsis or death related to sepsis. Since most of these studies were retrospective, the translational value in the real-world setting in different wards should be further investigated. 86.4% topic match

86.1%

0.0

2022

[236] MACHINE LEARNING TO DEVELOP A MODEL THAT PREDICTS EARLY IMPENDING SEPSIS IN NEUROSURGICAL PATIENTS Evgenios Vlachos, ..., and George Giannakopoulos Proceedings of the 12th Hellenic Conference on Artificial Intelligence 2022 - 0 citations - Show abstract - Cite 86.1% topic match

86.0%

1.2

2022

[237] Beyond technology: Can artificial intelligence support clinical decisions in the prediction of sepsis? Juliane de Souza Scherer, ..., and C. Bica Revista brasileira de enfermagem 2022 - 3 citations - Show abstract - Cite 86.0% topic match

85.9%

0.0

2023

[238] The Potential Application of Artificial Intelligence in Healthcare and Hospitals S. Rani, ..., and Prabhat R. Singh ITM Web of Conferences 2023 - 0 citations - Show abstract - Cite 85.9% topic match

85.8%

0.6

2019

[239] Anomaly Detection Semi-Supervised Framework for Sepsis Treatment Inès Krissaane, ..., and Richard D. Wilkinson 2019 Computing in Cardiology (CinC) 2019 - 3 citations - Show abstract - Cite 85.8% topic match

85.8%

0.9

2018

[240] Predicting Mortality of Sepsis Patients in a Multi-Site Healthcare System using Supervised Machine Learning Brittany M. Bogle, ..., and Abedi Journal Not Provided 2018 - 6 citations - Show abstract - Cite 85.8% topic match

85.8%

3.9

2019

[241] MGP-AttTCN: An interpretable machine learning model for the prediction of sepsis Margherita Rosnati and Vincent Fortuin PLoS ONE 2019 - 19 citations - Show abstract - Cite - PDF 85.8% topic match

85.7%

0.8

2019

[242] Ring-Topology Echo State Networks for ICU Sepsis Classification M. Alfaras, ..., and H. Gamboa 2019 Computing in Cardiology (CinC) 2019 - 4 citations - Show abstract - Cite 85.7% topic match

85.5%

2.1

2021

[243] Artificial Intelligence May Predict Early Sepsis After Liver Transplantation Rishikesan Kamaleswaran, ..., and D. Maluf Frontiers in Physiology 2021 - 6 citations - Show abstract - Cite 85.5% topic match

85.2%

1.0

2019

[244] Prediction of Sepsis Using LSTM Neural Network With Hyperparameter Optimization With a Genetic Algorithm P. Nejedly, ..., and P. Jurák 2019 Computing in Cardiology (CinC) 2019 - 5 citations - Show abstract - Cite 85.2% topic match

84.5%

0.4

2021

[245] A Machine Learning Understanding of Sepsis M. Shetty, ..., and Gowri Srinivasa 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) 2021 - 1 citations - Show abstract - Cite 84.5% topic match

84.2%

21.4

2018

[246] Multicenter validation of a sepsis prediction algorithm using only vital sign data in the emergency department, general ward and ICU Q. Mao, ..., and R. Das bioRxiv 2018 - 140 citations - Show abstract - Cite Abstract: Objectives We validate a machine learning-based sepsis prediction algorithm (InSight) for detection and prediction of three sepsis-related gold standards, using only six vital signs. We evaluate robustness to missing data, customization to site-specific data using transfer learning, and generalizability to new settings. Design A machine learning algorithm with gradient tree boosting. Features for prediction were created from combinations of only six vital sign measurements and their changes over time. Setting A mixed-ward retrospective data set from the University of California, San Francisco (UCSF) Medical Center (San Francisco, CA) as the primary source, an intensive care unit data set from the Beth Israel Deaconess Medical Center (Boston, MA) as a transfer learning source, and four additional institutions’ datasets to evaluate generalizability. Participants 684,443 total encounters, with 90,353 encounters from June 2011 to March 2016 at UCSF. Interventions none Primary and secondary outcome measures Area under the receiver operating characteristic curve (AUROC) for detection and prediction of sepsis, severe sepsis, and septic shock. Results For detection of sepsis and severe sepsis, InSight achieves an area under the receiver operating characteristic (AUROC) curve of 0.92 (95% CI 0.90 - 0.93) and 0.87 (95% CI 0.86 - 0.88), respectively. Four hours before onset, InSight predicts septic shock with an AUROC of 0.96 (95% CI 0.94 -0.98), and severe sepsis with an AUROC of 0.85 (95% CI 0.79 - 0.91). Conclusions InSight outperforms existing sepsis scoring systems in identifying and predicting sepsis, severe sepsis, and septic shock. This is the first sepsis screening system to exceed an AUROC of 0.90 using only vital sign inputs. InSight is robust to missing data, can be customized to novel hospital data using a small fraction of site data, and retained strong discrimination across all institutions. Strengths and limitations of this study Machine learning is applied to the detection and prediction of three separate sepsis standards in the emergency department, general ward and intensive care settings. Only six commonly measured vital signs are used as input for the algorithm. The algorithm is robust to randomly missing data. Transfer learning successfully leverages large dataset information to a target dataset. Retrospective nature of the study does not predict clinician reaction to information. 84.2% topic match

84.2%

1.8

2022

[247] Mortality prediction in ICU Using a Stacked Ensemble Model Na Ren, ..., and Xin Zhang Computational and Mathematical Methods in Medicine 2022 - 3 citations - Show abstract - Cite 84.2% topic match

Shows AI model effectiveness in ICU mortality prediction. Uses a stacked ensemble model with clinical severity scores to improve prediction accuracy. Focuses on mortality rather than early sepsis detection in ICU patients.

Shows AI model effectiveness in ICU mortality prediction. Uses a stacked ensemble model with clinical severity scores to improve prediction accuracy. Focuses on mortality rather than early sepsis detection in ICU patients.

84.1%

0.0

2017

[248] Pediatric Severe Sepsis Prediction Using Machine Learning Thomas Desautels, ..., and R. Das bioRxiv 2017 - 0 citations - Show abstract - Cite 84.1% topic match

84.0%

0.5

2022

[249] Data science in the intensive care unit Ming-hao Luo, ..., and Zhe Luo World Journal of Critical Care Medicine 2022 - 1 citations - Show abstract - Cite 84.0% topic match

83.7%

3.7

2021

[250] Unifying cardiovascular modelling with deep reinforcement learning for uncertainty aware control of sepsis treatment Thesath Nanayakkara, ..., and D. Swigon PLOS Digital Health 2021 - 13 citations - Show abstract - Cite - PDF 83.7% topic match

83.7%

23.3

2019

[251] An attention based deep learning model of clinical events in the intensive care unit Deepak A Kaji, ..., and E. Oermann PLoS ONE 2019 - 127 citations - Show abstract - Cite 83.7% topic match

83.5%

3.3

2021

[252] OnAI-Comp: An Online AI Experts Competing Framework for Early Sepsis Detection Anni Zhou, ..., and Rishikesan Kamaleswaran IEEE/ACM Transactions on Computational Biology and Bioinformatics 2021 - 9 citations - Show abstract - Cite 83.5% topic match

83.5%

0.0

2022

[253] 650-P: Artificial Intelligence and Individualized Optimal Glycemic Target in ICU Patients J. Yun, ..., and K. Song Diabetes 2022 - 0 citations - Show abstract - Cite Abstract: Introduction: Deep learning methods, commonly called artificial intelligence (AI) , have been widely adopted in medical research. Reinforcement learning is a particularly promising AI tool that can generate optimal strategies based on non-optimized training data. The aim of the currentstudy was to develop and validate a reinforcement learning algorithm for determining optimal glycemic targets for sepsis patients in the ICU. Methods: We developed and validated a clinical decision support model that provided an individualized daily glycemic target for each critically ill patient based on the retrospective analysis of two independent ICU databases, Medical Information for Mart for Intensive Care III (MIMIC-III) and the eICU Collaborative Research Database (eICU-CRD) . We used a Markov decision process (MDP) to formulate sequential decision-making. The discrete state was generated by quantizing all patients’ longitudinal health records using a k-means clustering algorithm. To evaluate clinician policy, we used the temporal-difference (TD) learning method. To learn AI policy, we generated a random action policy, updated the value function, and used the value function to update the policy. Results: Average return per patient was significantly higher in survivors than non-survivors, and a significant inverse relationship was observed between AI performance return and estimated 90-day mortality. Contrary to the current guidelines that recommend maintaining a glycemic range of 140-180 mg during ICU admission, AI most often recommended a glycemic range of 120-139 mg/dL for ICU patients. Analysis of mortality rate according to mean glucose level during ICU admission revealed that the greater the difference between AI recommendation and real glycemic control range, the higher the mortality rate. Conclusion: These results suggest that tighter glycemic control, guided by a similar AI policy for daily individualized optimal glycemic target, may help improve ICU patient survival. J.Yun: None. G.Lee: None. J.Kim: None. S.Ko: None. Y.Ahn: None. D.Kim: n/a. K.Song: n/a. 83.5% topic match

83.4%

0.0

2020

[254] Artificial intelligence in critical care: prediction of sepsis in patients in intensive care from first initial laboratory parameters S. Mitra and H. Sangwan International Journal of Research in Medical Sciences 2020 - 0 citations - Show abstract - Cite 83.4% topic match

83.4%

6.4

2020

[255] Validation of a machine learning algorithm for early severe sepsis prediction: a retrospective study predicting severe sepsis up to 48 h in advance using a diverse dataset from 461 US hospitals Hoyt J Burdick, ..., and R. Das BMC Medical Informatics and Decision Making 2020 - 24 citations - Show abstract - Cite 83.4% topic match

83.0%

1.3

2023

[256] Machine Learning for Early Outcome Prediction in Septic Patients in the Emergency Department M. Greco, ..., and Maurizio Cecconi Algorithms 2023 - 2 citations - Show abstract - Cite 83.0% topic match

82.9%

1.1

2019

[257] Data-driven Discovery of a Sepsis Patients Severity Prediction in the ICU via Pre-training BiLSTM Networks Qing Li, ..., and Junhao Hu 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) 2019 - 5 citations - Show abstract - Cite 82.9% topic match

82.9%

0.0

2022

[258] Examining Deep Learning Methods For The Detection Of Sepsis Anagha Anand, ..., and S. G 2022 6th International Conference On Computing, Communication, Control And Automation (ICCUBEA 2022 - 0 citations - Show abstract - Cite Abstract: Sepsis is a fatal syndrome that develops when the body reacts to an infection or virus, thereby, inducing inflammation which might result in organ dysfunction. Detecting sepsis at an earlier stage is critical, as a delay in antibiotic treatment has been reported to result in an increase in mortality rate, with a 7.6% increase in fatalities for individuals with critical sepsis condition every few hours the antibiotic administration is delayed. Hence, the earlier sepsis is detected and quicker the treatment is administered, the better the outcome for the patient and a reduced cost would have to be borne by the healthcare system. At present, there is no particular test to detect sepsis. Detection is usually done by keeping track of body temperature, heart rate etc. and conducting appropriate tests when organ failure occurs. This is not a reliable method and hence the need for better ways of detection arises. With the evolution of digital technology, Machine Learning (ML) has the ability to revolutionize medicine. Deep learning, a subset of ML, has gained immense popularity in recent times due to the ample quantity of data generated in various fields. Around 2.5 quintillion bytes of data are generated each day, according to statistics. As a result, the expansion of the world's economy is increasingly being attributed to big data. This paper presents a comparison of the classification report, accuracy and runtime of Neural Network, LSTM, and CNN on the public dataset proposed by PhysioNet Challenge 2019. The paper aims to study the effectiveness of different deep learning methods on clinical data. Data preprocessing involves handling missing values by imputation of mean, median and mode. SMOTE (Synthetic Minority Oversampling Technique) is an oversampling method that has been incorporated to manage imbalanced data by replicating minority class entries. The paper explains the advantages of CNN (Convolutional Neural Networks) that is capable of effective feature extraction and LSTM (Long short-term memory) that can assist in time series analysis and prediction. This will help estimate the theoretical resources required for performing the computation. This will provide a foundation for developing ensemble methods using these models and help understand its intricacies, advantages and disadvantages. 82.9% topic match

82.8%

0.0

2021

[259] Characterization of heart rate variability and oxygen saturation in sepsis patients Bilal Yaseen Al‐Mualemi and Lu Lu Expert Systems 2021 - 0 citations - Show abstract - Cite 82.8% topic match

82.7%

0.0

2023

[260] Can Predictive AI Improve Early Detection of Sepsis and Other Conditions? R. Voelker and Y. Hswen JAMA 2023 - 0 citations - Show abstract - Cite 82.7% topic match

82.6%

0.2

2018

[261] 1512: USING REAL-TIME DATA FOR ALGORITHMIC EARLY SEPSIS DETECTION IN NONCRITICAL CARE ENVIRONMENTS J. Guy, ..., and J. Perlin Critical Care Medicine 2018 - 1 citations - Show abstract - Cite Abstract: www.ccmjournal.org Critical Care Medicine • Volume 46 • Number 1 (Supplement) Learning Objectives: Substantial effort has been dedicated to developing automated detection and prediction algorithms to use healthcare data in the identification of potential sepsis. However, there have been few reports of the use of these algorithms in non-critical care environments and the implications on clinical workflow. Methods: We developed an automated algorithm for interpreting patient electronic physiologic and basic laboratory data from medical-surgical patients every 15 minutes. The algorithm was tested and validated at a 366 bed community hospital. The algorithm scored all medical-surgical patients admitted between April 12 and April 29, 2016. Algorithmic detection was compared to existing clinical protocol consisting of nurse sepsis screens at shift change or when deemed necessary by patient condition. No clinical action was taken as a result of the algorithm. Results: Of the 1,314 patients admitted to medical-surgical units during the testing period, the algorithm detected sepsis for 464 patients. Of these, 132 were true positive detections based on the results of nurse sepsis screens, giving the algorithm a sensitivity of 99% (132/133), specificity of 72% (849/1181) and positive predictive value of 28% (132/464). Following existing protocols, nursing staff performed sepsis screens on 734. The sensitivity of the nurse sepsis screens was 100% by definition (133/133). As a detector of sepsis, the nurse sepsis screens had a specificity of 49% (580/1181) and positive predictive value of 18% (133/734). Sepsis onset was defined as the documentation of the first positive sepsis screen in the nurse screening process; algorithmic detection preceded this by a median of 24 hours. Conclusions: Algorithmic detection of sepsis is possible using data from medical-surgical units. Using this algorithm in clinical workflows offers the opportunity for not only timelier treatment, but greater work efficiency by reducing the amount of time spent performing negative sepsis screens and more time for the actual care of sepsis and other patients. 82.6% topic match

81.6%

0.0

2023

[262] Conditional Tabular Generative Adversarial Net for Enhancing Ensemble Classifiers in Sepsis Diagnosis A. Alfakeeh, ..., and Thiago Pillonetto Appl. Comput. Intell. Soft Comput. 2023 - 0 citations - Show abstract - Cite Abstract: Antibiotic-resistant bacteria have proliferated at an alarming rate as a result of the extensive use of antibiotics and the paucity of new medication research. The possibility that an antibiotic-resistant bacterial infection would progress to sepsis is one of the major collateral problems affecting people with this condition. 31,000 lives were lost due to sepsis in England with costs about two billion pounds annually. This research aims to develop and evaluate several classification approaches to improve predicting sepsis and reduce the tendency of underdiagnosis in computer-aided predictive tools. This research employs medical datasets for patients diagnosed with sepsis, and it analyses the efficacy of ensemble machine learning techniques compared to nonensemble machine learning techniques and the significance of data balancing and conditional tabular generative adversarial nets for data augmentation in producing reliable diagnosis. The average F Score obtained by the nonensemble models trained in this paper is 0.83 compared to the ensemble techniques average of 0.94. Nonensemble techniques, such as Decision Tree, achieved an F score of 0.90, an AUC of 0.90, and an accuracy of 90%. Histogram-basedgradient boosting classification tree achieved an F score of 0.96, an AUC of 0.96, and an accuracy of 95%, surpassing the other models tested. Additionally, when compared to the current state-of-the-art sepsis prediction models, the models developed in this study demonstrated higher average performance in all metrics, indicating reduced bias and improved robustness through data balancing and conditional tabular generative adversarial nets for data augmentation. The study revealed that data balancing and augmentation on the ensemble machine learning algorithms boost the efficacy of clinical predictive models and can help clinics decide which data types are most important when examining patients and diagnosing sepsis early through intelligent human-machine interface. 81.6% topic match

81.5%

0.2

2019

[263] Demographic Information Initialized Stacked Gated Recurrent Unit for an Early Prediction of Sepsis Naoki Nonaka and J. Seita 2019 Computing in Cardiology (CinC) 2019 - 1 citations - Show abstract - Cite 81.5% topic match

80.5%

3.5

2011

[264] Severe sepsis mortality prediction with relevance vector machines V. Ribas, ..., and A. Vellido 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society 2011 - 44 citations - Show abstract - Cite 80.5% topic match

80.5%

0.0

2020

[265] Predicting Clinical Deterioration in Hospitals Laleh Jalali, ..., and J. Álvarez-Rodríguez 2020 IEEE International Conference on Big Data (Big Data) 2020 - 0 citations - Show abstract - Cite - PDF 80.5% topic match

80.2%

7.1

2020

[266] Atrial Fibrillation Detection During Sepsis: Study on MIMIC III ICU Data S. Bashar, ..., and K. Chon IEEE Journal of Biomedical and Health Informatics 2020 - 30 citations - Show abstract - Cite 80.2% topic match

80.2%

0.1

2016

[267] Investigating prognostic factors in sepsis using computational intelligence methods Carles Morales Boada Journal Not Provided 2016 - 1 citations - Show abstract - Cite Abstract: Sepsis is a major challenge in medicine. It is in fact a traversal condition affecting people of all ages and is not respectful of lifestyle choices. There are many diseases in medicine whose definition is uncertain and cause high rates of mortality in medical services, and Sepsis is a flagship example. In an intensive care unit (ICU), patients in an advanced stage of Sepsis carries a high burden, namely a high mortality rate (about 50%) and higher costs of treatment compared with other ICU patients. After an operation, patients have a tendency to develop a phenomenon related to the mechanism of immune system. The pathophysiology of Sepsis in humans is poorly understood, even is one of the main causes of death for non-coronary ICU patients. It is a traversal condition affecting people of all ages. This syndrome was defined by consensus statement in 1992 to consist of certain criteria. Severe sepsis was defined as organ failure in the setting of sepsis, and septic shock was defined as severe sepsis where the organ failure was hypotension. The ICU environment is one of the scenarios in which critical decision making tasks are most relevant with respect to the outcome for the patient, and it is in this specific context that this thesis tries to make a contribution. The research reported in this document deals with the problem of Sepsis data analysis in general. On the one hand, a causal relationship study is made over a set of roughly one hundred different ICU measurements to detect hidden patterns among them, and to find the direct conditioners of the patients outcome, by means of probabilistic approaches (i.e. Bayesian Networks). On the other hand, the problem of survival prediction in patients that have suffered Septic Shock is faced applying Computational Intelligence (i.e. Artificial Neural Networks) and Machine learning approaches (Support Vector Machines), and more specifically in two different approaches: (1) predicting directly the outcome of the patient and (2) predicting the organ dysfunction risk, that can also lead patient to death or severe cognitive consequences. The data set used in this work is the public available MEDAN database, which consists of 412 patients that have suffered abdominal Septic Shock, of whom 201 died. The data were recorded from 71 German Intensive Care Units from 1998 to 2002. 80.2% topic match

79.7%

0.5

2020

[268] Identification of the diagnostic signature of sepsis based on bioinformatic analysis of gene expression and machine learning. Qian Zhao, ..., and Jian-Guo Li Combinatorial chemistry & high throughput screening 2020 - 2 citations - Show abstract - Cite 79.7% topic match

79.5%

0.0

2021

[269] Using Gated Recurrent Units Models for Early Prediction of Sepsis in The Intensive Care Unit Xuze Zhao and B. Qu https://doi.org/10.21203/RS.3.RS-259370/V1 2021 - 0 citations - Show abstract - Cite 79.5% topic match

79.5%

9.7

2016

[270] Signatures of Subacute Potentially Catastrophic Illness in the ICU: Model Development and Validation* Travis J. Moss, ..., and J. Moorman Critical Care Medicine 2016 - 77 citations - Show abstract - Cite Abstract: Objectives: Patients in ICUs are susceptible to subacute potentially catastrophic illnesses such as respiratory failure, sepsis, and hemorrhage that present as severe derangements of vital signs. More subtle physiologic signatures may be present before clinical deterioration, when treatment might be more effective. We performed multivariate statistical analyses of bedside physiologic monitoring data to identify such early subclinical signatures of incipient life-threatening illness. Design: We report a study of model development and validation of a retrospective observational cohort using resampling (Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis type 1b internal validation) and a study of model validation using separate data (type 2b internal/external validation). Setting: University of Virginia Health System (Charlottesville), a tertiary-care, academic medical center. Patients: Critically ill patients consecutively admitted between January 2009 and June 2015 to either the neonatal, surgical/trauma/burn, or medical ICUs with available physiologic monitoring data. Interventions: None. Measurements and Main Results: We analyzed 146 patient-years of vital sign and electrocardiography waveform time series from the bedside monitors of 9,232 ICU admissions. Calculations from 30-minute windows of the physiologic monitoring data were made every 15 minutes. Clinicians identified 1,206 episodes of respiratory failure leading to urgent unplanned intubation, sepsis, or hemorrhage leading to multi-unit transfusions from systematic individual chart reviews. Multivariate models to predict events up to 24 hours prior had internally validated C-statistics of 0.61–0.88. In adults, physiologic signatures of respiratory failure and hemorrhage were distinct from each other but externally consistent across ICUs. Sepsis, on the other hand, demonstrated less distinct and inconsistent signatures. Physiologic signatures of all neonatal illnesses were similar. Conclusions: Subacute potentially catastrophic illnesses in three diverse ICU populations have physiologic signatures that are detectable in the hours preceding clinical detection and intervention. Detection of such signatures can draw attention to patients at highest risk, potentially enabling earlier intervention and better outcomes. 79.5% topic match

76.8%

0.8

2022

[271] [Artificial Intelligence: Challenges and Applications in Intensive Care Medicine]. Lukas Martin, ..., and J. Bickenbach Anasthesiologie, Intensivmedizin, Notfallmedizin, Schmerztherapie : AINS 2022 - 2 citations - Show abstract - Cite 76.8% topic match

76.7%

7.5

2021

[272] Early Prediction of Sepsis Based on Machine Learning Algorithm Xin Zhao, ..., and Guanjun Wang Computational Intelligence and Neuroscience 2021 - 21 citations - Show abstract - Cite 76.7% topic match

75.8%

3.0

2021

[273] Diagnostic and prognostic capabilities of a biomarker and EMR‐based machine learning algorithm for sepsis Ishan Taneja, ..., and R. Bashir Clinical and Translational Science 2021 - 10 citations - Show abstract - Cite 75.8% topic match

75.7%

0.6

2019

[274] Improving the Performance of a Neural Network for Early Prediction of Sepsis ByeongTak Lee, ..., and Yeha Lee 2019 Computing in Cardiology (CinC) 2019 - 3 citations - Show abstract - Cite 75.7% topic match

75.7%

0.0

2023

[275] Machine Learning Models for Early Prediction of Malignancy in Sepsis Using Clinical Dataset Divya Bhaskaracharya and Diya Mehta 2023 International Conference on Smart Systems for applications in Electrical Sciences (ICSSES) 2023 - 0 citations - Show abstract - Cite 75.7% topic match

75.1%

0.0

2020

[276] Prior Prophecy of Septicemia Through Machine Learning Manikandan R, ..., and Durga E Intelligent Systems and Computer Technology 2020 - 0 citations - Show abstract - Cite 75.1% topic match

74.8%

8.7

2021

[277] Evaluating machine learning models for sepsis prediction: A systematic review of methodologies Hongfei Deng, ..., and Hua Jiang iScience 2021 - 23 citations - Show abstract - Cite 74.8% topic match

74.4%

1.6

2021

[278] Offline reinforcement learning with uncertainty for treatment strategies in sepsis Ran Liu, ..., and R. Winslow ArXiv 2021 - 5 citations - Show abstract - Cite - PDF 74.4% topic match

74.3%

1.2

2020

[279] Implementation of an Automated Sepsis Screening Tool in a Community Hospital Setting. P. Cooper, ..., and A. Markham Journal of Nursing Care Quality 2020 - 5 citations - Show abstract - Cite 74.3% topic match

74.2%

2.6

2021

[280] Early Prediction of Mortality in Critical Care Setting in Sepsis Patients Using Structured Features and Unstructured Clinical Notes Jiyoung Shin, ..., and Yuan Luo 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) 2021 - 7 citations - Show abstract - Cite - PDF 74.2% topic match

74.1%

0.3

2021

[281] Algorithmic prognostication in critical care: a promising but unproven technology for supporting difficult decisions G. Weissman and V. Liu Current Opinion in Critical Care 2021 - 1 citations - Show abstract - Cite 74.1% topic match

74.0%

4.2

2022

[282] Artificial Intelligence for the Prediction of In-Hospital Clinical Deterioration: A Systematic Review L. Veldhuis, ..., and J. Ludikhuize Critical Care Explorations 2022 - 8 citations - Show abstract - Cite Abstract: OBJECTIVES: To analyze the available literature on the performance of artificial intelligence-generated clinical models for the prediction of serious life-threatening events in non-ICU adult patients and evaluate their potential clinical usage. DATA SOURCES: The PubMed database was searched for relevant articles in English literature from January 1, 2000, to January 23, 2022. Search terms, including artificial intelligence, machine learning, deep learning, and deterioration, were both controlled terms and free-text terms. STUDY SELECTION: We performed a systematic search reporting studies that showed performance of artificial intelligence-based models with outcome mortality and clinical deterioration. DATA EXTRACTION: Two review authors independently performed study selection and data extraction. Studies with the same outcome were grouped, namely mortality and various forms of deterioration (including ICU admission, adverse events, and cardiac arrests). Meta-analysis was planned in case sufficient data would be extracted from each study and no considerable heterogeneity between studies was present. DATA SYNTHESIS: In total, 45 articles were included for analysis, in which multiple methods of artificial intelligence were used. Twenty-four articles described models for the prediction of mortality and 21 for clinical deterioration. Due to heterogeneity of study characteristics (patient cohort, outcomes, and prediction models), meta-analysis could not be performed. The main reported measure of performance was the area under the receiver operating characteristic (AUROC) (n = 38), of which 33 (87%) had an AUROC greater than 0.8. The highest reported performance in a model predicting mortality had an AUROC of 0.935 and an area under the precision-recall curve of 0.96. CONCLUSIONS: Currently, a growing number of studies develop and analyzes artificial intelligence-based prediction models to predict critical illness and deterioration. We show that artificial intelligence-based prediction models have an overall good performance in predicting deterioration of patients. However, external validation of existing models and its performance in a clinical setting is highly recommended. 74.0% topic match

73.8%

1.9

2022

[283] Learning Optimal Treatment Strategies for Sepsis Using Offline Reinforcement Learning in Continuous Space Zeyu Wang, ..., and Ming Sheng International Conference on Health Information Science 2022 - 4 citations - Show abstract - Cite - PDF 73.8% topic match

73.8%

0.0

2022

[284] Sepsis Detection using Neural Networks S. Babu, ..., and Lakshmi Lahari Appala 2022 International Conference on Smart Generation Computing, Communication and Networking (SMART GENCON) 2022 - 0 citations - Show abstract - Cite 73.8% topic match

73.7%

0.0

2020

[285] A Deep Learning Model for Early Prediction of Sepsis from Intensive Care Unit Records R. Zhao, ..., and Zengchang Qin International Conference on Neural Information Processing 2020 - 0 citations - Show abstract - Cite 73.7% topic match

73.7%

0.0

2023

[286] Comparison of Explainable Machine-Learning Models for Decision-Making in Health Intensive Care Using SHapley Additive exPlanations Igor Pereira Vidal, ..., and E. Maziero Proceedings of the XIX Brazilian Symposium on Information Systems 2023 - 0 citations - Show abstract - Cite 73.7% topic match

73.6%

0.0

2023

[287] Reinforcement Learning for Real-time ICU Patient Management in Critical Care Vandana Roy, ..., and Sanjay Kumar Sharma 2023 International Conference on System, Computation, Automation and Networking (ICSCAN) 2023 - 0 citations - Show abstract - Cite 73.6% topic match

73.2%

0.0

2019

[288] Portable Early Prediction of Sepsis from Clinical Data on Intel Myriad X P. Mathur, ..., and Fabio Fracas Journal Not Provided 2019 - 0 citations - Show abstract - Cite 73.2% topic match

73.1%

4.0

2024

[289] Early Prediction of Mortality for Septic Patients Visiting Emergency Room Based on Explainable Machine Learning: A Real-World Multicenter Study S. Park, ..., and J. Heo Journal of Korean Medical Science 2024 - 2 citations - Show abstract - Cite Abstract: Background Worldwide, sepsis is the leading cause of death in hospitals. If mortality rates in patients with sepsis can be predicted early, medical resources can be allocated efficiently. We constructed machine learning (ML) models to predict the mortality of patients with sepsis in a hospital emergency department. Methods This study prospectively collected nationwide data from an ongoing multicenter cohort of patients with sepsis identified in the emergency department. Patients were enrolled from 19 hospitals between September 2019 and December 2020. For acquired data from 3,657 survivors and 1,455 deaths, six ML models (logistic regression, support vector machine, random forest, extreme gradient boosting [XGBoost], light gradient boosting machine, and categorical boosting [CatBoost]) were constructed using fivefold cross-validation to predict mortality. Through these models, 44 clinical variables measured on the day of admission were compared with six sequential organ failure assessment (SOFA) components (PaO2/FIO2 [PF], platelets (PLT), bilirubin, cardiovascular, Glasgow Coma Scale score, and creatinine). The confidence interval (CI) was obtained by performing 10,000 repeated measurements via random sampling of the test dataset. All results were explained and interpreted using Shapley’s additive explanations (SHAP). Results Of the 5,112 participants, CatBoost exhibited the highest area under the curve (AUC) of 0.800 (95% CI, 0.756–0.840) using clinical variables. Using the SOFA components for the same patient, XGBoost exhibited the highest AUC of 0.678 (95% CI, 0.626–0.730). As interpreted by SHAP, albumin, lactate, blood urea nitrogen, and international normalization ratio were determined to significantly affect the results. Additionally, PF and PLTs in the SOFA component significantly influenced the prediction results. Conclusion Newly established ML-based models achieved good prediction of mortality in patients with sepsis. Using several clinical variables acquired at the baseline can provide more accurate results for early predictions than using SOFA components. Additionally, the impact of each variable was identified. 73.1% topic match

72.7%

16.8

2022

[290] Machine learning for the prediction of acute kidney injury in patients with sepsis S. Yue, ..., and Jiayuan Wu Journal of Translational Medicine 2022 - 37 citations - Show abstract - Cite 72.7% topic match

71.8%

0.0

2019

[291] Advances in the application of artificial intelligence in critical care medicine F. Xie, ..., and J. Bian International Journal of Anesthesiology and Resuscitation 2019 - 0 citations - Show abstract - Cite 71.8% topic match

71.8%

1.2

2019

[292] Early Sepsis Prediction Using Ensemble Learning with Features Extracted from LSTM Recurrent Neural Network Zhengling He, ..., and Yichen Pan 2019 Computing in Cardiology (CinC) 2019 - 6 citations - Show abstract - Cite 71.8% topic match

70.6%

4.8

2021

[293] Early Detection of Septic Shock Onset Using Interpretable Machine Learners Debdipto Misra, ..., and V. Abedi Journal of Clinical Medicine 2021 - 17 citations - Show abstract - Cite Abstract: Background: Developing a decision support system based on advances in machine learning is one area for strategic innovation in healthcare. Predicting a patient’s progression to septic shock is an active field of translational research. The goal of this study was to develop a working model of a clinical decision support system for predicting septic shock in an acute care setting for up to 6 h from the time of admission in an integrated healthcare setting. Method: Clinical data from Electronic Health Record (EHR), at encounter level, were used to build a predictive model for progression from sepsis to septic shock up to 6 h from the time of admission; that is, T = 1, 3, and 6 h from admission. Eight different machine learning algorithms (Random Forest, XGBoost, C5.0, Decision Trees, Boosted Logistic Regression, Support Vector Machine, Logistic Regression, Regularized Logistic, and Bayes Generalized Linear Model) were used for model development. Two adaptive sampling strategies were used to address the class imbalance. Data from two sources (clinical and billing codes) were used to define the case definition (septic shock) using the Centers for Medicare & Medicaid Services (CMS) Sepsis criteria. The model assessment was performed using Area under Receiving Operator Characteristics (AUROC), sensitivity, and specificity. Model predictions for each feature window (1, 3 and 6 h from admission) were consolidated. Results: Retrospective data from April 2005 to September 2018 were extracted from the EHR, Insurance Claims, Billing, and Laboratory Systems to create a dataset for septic shock detection. The clinical criteria and billing information were used to label patients into two classes-septic shock patients and sepsis patients at three different time points from admission, creating two different case-control cohorts. Data from 45,425 unique in-patient visits were used to build 96 prediction models comparing clinical-based definition versus billing-based information as the gold standard. Of the 24 consolidated models (based on eight machine learning algorithms and three feature windows), four models reached an AUROC greater than 0.9. Overall, all the consolidated models reached an AUROC of at least 0.8820 or higher. Based on the AUROC of 0.9483, the best model was based on Random Forest, with a sensitivity of 83.9% and specificity of 88.1%. The sepsis detection window at 6 h outperformed the 1 and 3-h windows. The sepsis definition based on clinical variables had improved performance when compared to the sepsis definition based on only billing information. Conclusion: This study corroborated that machine learning models can be developed to predict septic shock using clinical and administrative data. However, the use of clinical information to define septic shock outperformed models developed based on only administrative data. Intelligent decision support tools can be developed and integrated into the EHR and improve clinical outcomes and facilitate the optimization of resources in real-time. 70.6% topic match

70.1%

2.3

2021

[294] Predicting and Responding to Clinical Deterioration in Hospitalized Patients by Using Artificial Intelligence: Protocol for a Mixed Methods, Stepped Wedge Study Laura M. Holdsworth, ..., and Ron C. Li JMIR Research Protocols 2021 - 8 citations - Show abstract - Cite Abstract: Background The early identification of clinical deterioration in patients in hospital units can decrease mortality rates and improve other patient outcomes; yet, this remains a challenge in busy hospital settings. Artificial intelligence (AI), in the form of predictive models, is increasingly being explored for its potential to assist clinicians in predicting clinical deterioration. Objective Using the Systems Engineering Initiative for Patient Safety (SEIPS) 2.0 model, this study aims to assess whether an AI-enabled work system improves clinical outcomes, describe how the clinical deterioration index (CDI) predictive model and associated work processes are implemented, and define the emergent properties of the AI-enabled work system that mediate the observed clinical outcomes. Methods This study will use a mixed methods approach that is informed by the SEIPS 2.0 model to assess both processes and outcomes and focus on how physician-nurse clinical teams are affected by the presence of AI. The intervention will be implemented in hospital medicine units based on a modified stepped wedge design featuring three stages over 11 months—stage 0 represents a baseline period 10 months before the implementation of the intervention; stage 1 introduces the CDI predictions to physicians only and triggers a physician-driven workflow; and stage 2 introduces the CDI predictions to the multidisciplinary team, which includes physicians and nurses, and triggers a nurse-driven workflow. Quantitative data will be collected from the electronic health record for the clinical processes and outcomes. Interviews will be conducted with members of the multidisciplinary team to understand how the intervention changes the existing work system and processes. The SEIPS 2.0 model will provide an analytic framework for a mixed methods analysis. Results A pilot period for the study began in December 2020, and the results are expected in mid-2022. Conclusions This protocol paper proposes an approach to evaluation that recognizes the importance of assessing both processes and outcomes to understand how a multifaceted AI-enabled intervention affects the complex team-based work of identifying and managing clinical deterioration. International Registered Report Identifier (IRRID) PRR1-10.2196/27532 70.1% topic match

Explores AI's role in predicting clinical deterioration in hospitals. Utilizes AI predictive models to enhance clinicians' ability to anticipate patient decline, aiming to improve outcomes. Focuses not specifically on sepsis or ICU patients, but on broader hospital patient deterioration.

Explores AI's role in predicting clinical deterioration in hospitals. Utilizes AI predictive models to enhance clinicians' ability to anticipate patient decline, aiming to improve outcomes. Focuses not specifically on sepsis or ICU patients, but on broader hospital patient deterioration.

69.2%

1.2

2022

[295] Reinforcement Learning For Sepsis Treatment: A Continuous Action Space Solution Yong Huang, ..., and Amir-Mohammad Rahmani Machine Learning in Health Care 2022 - 3 citations - Show abstract - Cite 69.2% topic match

69.2%

3.3

2021

[296] Outcomes prediction in longitudinal data: Study designs evaluation, use case in ICU acquired sepsis M. Schvetz, ..., and Robert Moskovitch Journal of biomedical informatics 2021 - 11 citations - Show abstract - Cite 69.2% topic match

69.1%

15.3

2018

[297] Applying Artificial Intelligence to Identify Physiomarkers Predicting Severe Sepsis in the PICU* Rishikesan Kamaleswaran, ..., and Samir H. Shah Pediatric Critical Care Medicine 2018 - 89 citations - Show abstract - Cite Abstract: Objectives: We used artificial intelligence to develop a novel algorithm using physiomarkers to predict the onset of severe sepsis in critically ill children. Design: Observational cohort study. Setting: PICU. Patients: Children age between 6 and 18 years old. Interventions: None. Measurements and Main Results: Continuous minute-by-minute physiologic data were available for a total of 493 critically ill children admitted to a tertiary care PICU over an 8-month period, 20 of whom developed severe sepsis. Using an alert time stamp generated by an electronic screening algorithm as a reference point, we studied up to 24 prior hours of continuous physiologic data. We identified physiomarkers, including SD of heart rate, systolic and diastolic blood pressure, and symbolic transitions probabilities of those variables that discriminated severe sepsis patients from controls (all other patients admitted to the PICU who did not meet severe sepsis criteria). We used logistic regression, random forests, and deep Convolutional Neural Network methods to derive our models. Analysis was performed using data generated in two windows prior to the firing of the electronic screening algorithm, namely, 2–8 and 8–24 hours. When analyzing the physiomarkers present in the 2–8 hours analysis window, logistic regression performed with specificity of 87.4% and sensitivity of 55.0%, random forest performed with 79.6% specificity and 80.0% sensitivity, and the Convolutional Neural Network performed with 83.0% specificity and 75.0% sensitivity. When analyzing physiomarkers from the 8–24 hours window, logistic regression resulted in 77.1% specificity and 39.3% sensitivity, random forest performed with 82.3% specificity and 61.1% sensitivity, whereas the Convolutional Neural Network method achieved 81% specificity and 76% sensitivity. Conclusions: Artificial intelligence can be used to predict the onset of severe sepsis using physiomarkers in critically ill children. Further, it may detect severe sepsis as early as 8 hours prior to a real-time electronic severe sepsis screening algorithm. 69.1% topic match

68.4%

0.0

2023

[298] Supervised reinforcement learning for recommending treatment strategies in sepsis Haoran Sun, ..., and Yujing Yang https://doi.org/10.1117/12.2689783 2023 - 0 citations - Show abstract - Cite 68.4% topic match

68.4%

2.4

2019

[299] Temporal Convolutional Networks and Dynamic Time Warping can Drastically Improve the Early Prediction of Sepsis Michael Moor, ..., and K. Borgwardt ArXiv 2019 - 13 citations - Show abstract - Cite - PDF 68.4% topic match

68.1%

9.2

2009

[300] Validation of a screening tool for the early identification of sepsis. Laura J. Moore, ..., and Frederick A. Moore The Journal of trauma 2009 - 140 citations - Show abstract - Cite 68.1% topic match

67.2%

17.8

2019

[301] Evaluation of a machine learning algorithm for up to 48-hour advance prediction of sepsis using six vital signs C. Barton, ..., and R. Das Computers in biology and medicine 2019 - 92 citations - Show abstract - Cite 67.2% topic match

67.0%

0.9

2021

[302] Learning to Treat Hypotensive Episodes in Sepsis Patients Using a Counterfactual Reasoning Framework R. Jeter, ..., and S. Nemati medRxiv 2021 - 3 citations - Show abstract - Cite 67.0% topic match

66.8%

0.0

2024

[303] [Research progress of artificial intelligence technology in early diagnosis of sepsis]. Xiaoqian Wang and Wenjie Qi Zhonghua wei zhong bing ji jiu yi xue 2024 - 0 citations - Show abstract - Cite 66.8% topic match

63.8%

0.0

2020

[304] Early Detection of Sepsis using Machine Learning No author found International Journal of Recent Technology and Engineering 2020 - 0 citations - Show abstract - Cite 63.8% topic match

63.1%

1.6

2021

[305] A self-supervised method for treatment recommendation in sepsis Sihan Zhu and Jian Pu Frontiers of Information Technology & Electronic Engineering 2021 - 5 citations - Show abstract - Cite 63.1% topic match

63.0%

7.6

2018

[306] Model-Based Reinforcement Learning for Sepsis Treatment Aniruddh Raghu, ..., and Sumeetpal S. Singh ArXiv 2018 - 43 citations - Show abstract - Cite - PDF 63.0% topic match

62.7%

24.0

2017

[307] Continuous State-Space Models for Optimal Sepsis Treatment: a Deep Reinforcement Learning Approach Aniruddh Raghu, ..., and M. Ghassemi Machine Learning in Health Care 2017 - 172 citations - Show abstract - Cite - PDF 62.7% topic match

62.4%

0.0

2023

[308] Adaptive Learning and AI to Support Medication Management João Oliveira, ..., and R. Jardim-Gonçalves 2023 IEEE International Conference on Engineering, Technology and Innovation (ICE/ITMC) 2023 - 0 citations - Show abstract - Cite 62.4% topic match

62.2%

19.9

2020

[309] Using machine learning methods to predict in-hospital mortality of sepsis patients in the ICU G. Kong, ..., and Yonghua Hu BMC Medical Informatics and Decision Making 2020 - 76 citations - Show abstract - Cite 62.2% topic match

62.1%

8.9

2019

[310] Mortality Prediction of Septic Patients in the Emergency Department Based on Machine Learning J. Perng, ..., and Chih-Min Su Journal of Clinical Medicine 2019 - 42 citations - Show abstract - Cite 62.1% topic match

62.0%

13.4

2019

[311] Pediatric Severe Sepsis Prediction Using Machine Learning S. Le, ..., and R. Das Frontiers in Pediatrics 2019 - 64 citations - Show abstract - Cite 62.0% topic match

61.5%

0.5

2022

[312] Sepsis Prediction with Temporal Convolutional Networks Xing Wang and Yuntian He ArXiv 2022 - 1 citations - Show abstract - Cite - PDF 61.5% topic match

60.9%

2.8

2018

[313] Learning to Treat Sepsis with Multi-Output Gaussian Process Deep Recurrent Q-Networks Joseph D. Futoma, ..., and K. Heller Journal Not Provided 2018 - 18 citations - Show abstract - Cite 60.9% topic match

60.5%

3.5

2020

[314] Safe Reinforcement Learning for Sepsis Treatment Yan Jia, ..., and I. Habli 2020 IEEE International Conference on Healthcare Informatics (ICHI) 2020 - 13 citations - Show abstract - Cite 60.5% topic match

59.9%

0.0

2017

[315] Abstract 14999: Effect of a Machine Learning-Based Severe Sepsis Prediction Algorithm on Patient Survival and Hospital Length of Stay C. Barton, ..., and R. Das Circulation 2017 - 0 citations - Show abstract - Cite 59.9% topic match

59.8%

4.2

2020

[316] Too Many Definitions of Sepsis: Can Machine Learning Leverage the Electronic Health Record to Increase Accuracy and Bring Consensus? S. Saria and K. Henry Critical Care Medicine 2020 - 19 citations - Show abstract - Cite 59.8% topic match

59.3%

0.7

2017

[317] Predicting Mortality of Intensive Care Patients via Learning about Hazard D. H. Lee and E. Horvitz AAAI Conference on Artificial Intelligence 2017 - 5 citations - Show abstract - Cite 59.3% topic match

58.8%

1.4

2019

[318] Novel Imputing Method and Deep Learning Techniques for Early Prediction of Sepsis in Intensive Care Units Edwar Macias Toro, ..., and Antoni Morell 2019 Computing in Cardiology (CinC) 2019 - 7 citations - Show abstract - Cite 58.8% topic match

56.8%

0.0

2022

[319] Comparison of Machine Learning Algorithms for Sepsis Detection Asad Ullah, ..., and Auliya Rahman Vol 4 Issue 1 2022 - 0 citations - Show abstract - Cite 56.8% topic match

56.6%

0.0

2020

[320] Non-Invasive Prediction Model to Detect Sepsis using Supervised Machine Learning Algorithms No author found International Journal of Recent Technology and Engineering 2020 - 0 citations - Show abstract - Cite 56.6% topic match

53.9%

1.2

2022

[321] EARLY PREDICTION OF SEPSIS FROM CLINICAL DATA USING AI & ML Anusha and Nation Raj K Halli Journal Not Provided 2022 - 3 citations - Show abstract - Cite 53.9% topic match

53.9%

2.6

2021

[322] Contextual Embeddings from Clinical Notes Improves Prediction of Sepsis Fatemeh Amrollahi, ..., and S. Nemati AMIA ... Annual Symposium proceedings. AMIA Symposium 2021 - 9 citations - Show abstract - Cite 53.9% topic match

53.6%

0.0

2021

[323] DETECTION OF SEPSIS USING THE ANALYSIS OF MACHINE LEARNING ALGORITHMS No author found Journal Not Provided 2021 - 0 citations - Show abstract - Cite 53.6% topic match

52.9%

0.4

2019

[324] A Low Dimensional Algorithm for Detection of Sepsis From Electronic Medical Record Data Aruna Deogire 2019 Computing in Cardiology (CinC) 2019 - 2 citations - Show abstract - Cite 52.9% topic match

51.7%

1.8

2016

[325] Development and Validation of an Automated Sepsis Risk Assessment System. Ji-Sun Back, ..., and Sun-Mi Lee Research in nursing & health 2016 - 14 citations - Show abstract - Cite 51.7% topic match

51.2%

0.7

2023

[326] In-Sensor Artificial Intelligence and Fusion With Electronic Medical Records for At-Home Monitoring Sudarsan Sadasivuni, ..., and A. Sanyal IEEE Transactions on Biomedical Circuits and Systems 2023 - 1 citations - Show abstract - Cite 51.2% topic match

50.3%

0.0

2019

[327] A Predictive Model Based on Machine Learning for the Early Detection of Late-Onset Neonatal Sepsis: Development and Observational Study (Preprint) Wongeun Song, ..., and Sooyoung Yoo https://doi.org/10.2196/preprints.15965 2019 - 0 citations - Show abstract - Cite Abstract: BACKGROUND Neonatal sepsis is associated with most cases of mortalities and morbidities in the neonatal intensive care unit (NICU). Many studies have developed prediction models for the early diagnosis of bloodstream infections in newborns, but there are limitations to data collection and management because these models are based on high-resolution waveform data. OBJECTIVE The aim of this study was to examine the feasibility of a prediction model by using noninvasive vital sign data and machine learning technology. METHODS We used electronic medical record data in intensive care units published in the Medical Information Mart for Intensive Care III clinical database. The late-onset neonatal sepsis (LONS) prediction algorithm using our proposed forward feature selection technique was based on NICU inpatient data and was designed to detect clinical sepsis 48 hours before occurrence. The performance of this prediction model was evaluated using various feature selection algorithms and machine learning models. RESULTS The performance of the LONS prediction model was found to be comparable to that of the prediction models that use invasive data such as high-resolution vital sign data, blood gas estimations, blood cell counts, and pH levels. The area under the receiver operating characteristic curve of the 48-hour prediction model was 0.861 and that of the onset detection model was 0.868. The main features that could be vital candidate markers for clinical neonatal sepsis were blood pressure, oxygen saturation, and body temperature. Feature generation using kurtosis and skewness of the features showed the highest performance. CONCLUSIONS The findings of our study confirmed that the LONS prediction model based on machine learning can be developed using vital sign data that are regularly measured in clinical settings. Future studies should conduct external validation by using different types of data sets and actual clinical verification of the developed model. 50.3% topic match

49.9%

0.9

2010

[328] Temporal Features and Kernel Methods for Predicting Sepsis in Postoperative Patients JooSeuk Kim, ..., and C. Scott Journal Not Provided 2010 - 13 citations - Show abstract - Cite 49.9% topic match

49.9%

0.9

2022

[329] Identifying the Risk of Sepsis in Patients With Cancer Using Digital Health Care Records: Machine Learning–Based Approach Donghun Yang, ..., and H. Paik JMIR Medical Informatics 2022 - 2 citations - Show abstract - Cite 49.9% topic match

49.7%

0.6

2016

[330] Early warnings of heart rate deterioration Vânia Almeida and I. Nabney 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) 2016 - 5 citations - Show abstract - Cite 49.7% topic match

48.6%

0.2

2020

[331] Improving Treatment Decisions for Sepsis Patients by Reinforcement Learning R. Lyu Journal Not Provided 2020 - 1 citations - Show abstract - Cite Abstract: Sepsis is defined as a dysregulated immune response to infection leading to acute life-threatening organ dysfunction. Patients with sepsis have 25.8% intensive care unit (ICU) mortality, which was significantly higher than in the general ICU population. Making optimal medication decisions becomes an emergent and important task. The purpose of this study is to develop a data-driven decision-making tool that can dynamically suggest optimal treatments for each individual ICU patient with sepsis, and help clinicians make better treatment decisions to improve patients’ long-term survival outcomes. Model-free Q-learning was applied to data extracted from the eICU Research Institute (eRI) database. We selected 3,800 patients admitted to ICUs with septic shock and summarized their first 7 days of lab results and vitals into 18,014 daily records. To identify best treatment decisions of vasopressor use, we first clustered patients’ demographics and daily medical conditions into 100 distinct states. We then mapped ICU survival to time-dependent rewards and estimated the Q-values for each action taken at each state using temporal-difference learning. Finally, we obtained the optimal policy that maximizes the action-value function by policy iteration. An off-policy evaluation method was implemented to evaluate the performance of several treatment policies. The result showed that the Q-learning policy has significantly higher long-term average reward than the clinician policy or the random policy, meaning that patients who received treatments matching those suggested by the Q-learning policy had better survival outlook than those who did not. In conclusion, we showcased that the prospect of long-term survival may be improved through using modern reinforcement learning methods that optimizes the rewards against the dynamics of the environment. Public Health Significance: We developed a data-driven automatic reinforcement learning tool and applied it to an electronic health database of sepsis patients. The result showed that medical decisions that matched our Q-leaning policy led to better survival outlook; this suggests that machine learning can be used to help clinicians decide the most effective treatments and reduce the burden on medical and economical resources. 48.6% topic match

48.3%

0.9

2015

[332] Predicting hyperlactatemia in the MIMIC II database M. Dunitz, ..., and T. Heldt 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) 2015 - 8 citations - Show abstract - Cite 48.3% topic match

47.7%

0.0

2023

[333] Utilizing machine learning to create a blood-based scoring system for sepsis detection Sadik Aref European Journal of Clinical and Experimental Medicine 2023 - 0 citations - Show abstract - Cite 47.7% topic match

46.8%

0.0

2023

[334] Conventional and unconventional T cell responses contribute to the prediction of clinical outcome and causative bacterial pathogen in sepsis patients Ross J. Burton, ..., and Matthias Eberl Clinical and experimental immunology 2023 - 0 citations - Show abstract - Cite 46.8% topic match

46.0%

2.9

2022

[335] Superhuman performance on sepsis MIMIC-III data by distributional reinforcement learning Markus Böck, ..., and C. Heitzinger PLOS ONE 2022 - 5 citations - Show abstract - Cite 46.0% topic match

43.5%

0.6

2022

[336] Online Critical-State Detection of Sepsis Among ICU Patients using Jensen-Shannon Divergence Jeffrey O. Smith, ..., and Rishikesan Kamaleswaran AMIA ... Annual Symposium proceedings. AMIA Symposium 2022 - 1 citations - Show abstract - Cite - PDF 43.5% topic match

43.5%

2.7

2015

[337] Predictive models for severe sepsis in adult ICU patients Joseph Guillén, ..., and L. Barnes 2015 Systems and Information Engineering Design Symposium 2015 - 25 citations - Show abstract - Cite 43.5% topic match

43.1%

0.3

2021

[338] Establishment of a Highly Predictive Survival Nomogram For Patients With Sepsis: A Retrospective Cohort Study Hui Liu, ..., and Haiyan Yin https://doi.org/10.21203/RS.3.RS-218217/V1 2021 - 1 citations - Show abstract - Cite Abstract: Background: Sepsis is a critical illness common in intensive care units (ICUs) and emergency rooms worldwide and is associated with high morbidity and mortality. However, exisiting methods to predict mortality from sepsis, such as the Sequential Organ Failure Assessment (SOFA) score, are insufficient. This paper aimed to construct a nomogram for predicting the 30-, 60-, and 90-days mortality risks of patients with sepsis that is more accurate than the SOFA score alone. Methods: Data on sepsis patients were obtained from the Medical Information Mart for Intensive Care (MIMIC) database and analysed retrospectively. The included patients were randomly divided into a training cohort and a validation cohort. The variables included in the training cohort were selected using a backward stepwise selection method with Cox regression, which were then used to construct a prognostic nomogram. In the validation cohort, we compared our prognostic nomogram with the existing SOFA using the area under the time-dependent receiver operating characteristic curve (AUC), net reclassification improvement (NRI), integrated discrimination improvement (IDI), calibration plotting and decision-curve analysis (DCA).Results: We included a total of 5240 patients in the study, who were divided into the training (n=3667) and validation (n=1573) cohorts. Patient age and the following clinical parameters obtained on the first day of ICU admission were included in the nomogram: SOFA score, metastatic cancer, SpO2, lactate, body temperature, albumin, and red blood cell distribution width (RDW). The AUCs for the 30-, 60-, and 90-days mortality risks were better for our nomogram than for the SOFA score, with values of 0.766, 0.771, and 0.772, respectively, in the training cohort and 0.759, 0.770, and 0.760, respectively, in the validation cohort. The nomogram also showed good calibration, as indicated by the evidence that the predicted values of the survival risks at 30-, 60-and 90-days were in good agreement with the observed values both in the training and validation sets. In addition, IDI and NRI improved over the entire follow-up period. Finally, DCA was used to verify the clinical value of the model and its impact on actual decision-making. We can see that the net benefit of the nomogram is greater than the SOFA score for any predicted probability, both in the training set and in the validation set, indicating that it has a substantial net benefit in predicting 30-, 60-, and 90-days survival rates. Conclusions: We established a nomogram that performed better than the SOFA score in predicting the prognosis of patients with sepsis. Further studies with a large sample size are needed to verify the generalizability of the nomogram. 43.1% topic match

42.7%

1.3

2011

[339] Predictive monitoring for early detection of subacute potentially catastrophic illnesses in critical care J. Moorman, ..., and D. Lake 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society 2011 - 17 citations - Show abstract - Cite 42.7% topic match

42.3%

0.0

2022

[340] Cloud-Based Sepsis Prediction System with Neural Architecture Search Service Yen-Han Chiang, ..., and Yi-Lun Pan 2022 International Conference on Computational Science and Computational Intelligence (CSCI) 2022 - 0 citations - Show abstract - Cite 42.3% topic match

40.6%

0.2

2019

[341] Sepsis Detection Using Missingness Information Clémentine Aguet, ..., and M. Lemay 2019 Computing in Cardiology (CinC) 2019 - 1 citations - Show abstract - Cite 40.6% topic match

40.5%

0.4

2009

[342] Comparison of Analytic Approaches for Determining Variables - A Case Study in Predicting the Likelihood of Sepsis F. Gwadry-Sridhar, ..., and Michael Bauer International Conference on Health Informatics 2009 - 6 citations - Show abstract - Cite 40.5% topic match

39.2%

0.0

2019

[343] New Tool for Severe Sepsis, Septic Shock Diagnosis No author found Journal Not Provided 2019 - 0 citations - Show abstract - Cite Abstract: A new study, published in BMC Medical Informatics and Decision Making, aimed to determine the diagnostic accuracy of an electronic alert system in detecting severe sepsis or septic shock in ED patients. The study was carried out at a tertiary academic medical centre in Saudi Arabia. The results showed high specificity and sensitivity and negative predictive values of the alert system. Severe sepsis and septic shock are responsible for significant morbidity and mortality. In the United States, sepsis mortality reportedly occurs in 65.5 per 100,000 persons. Notably, the incidence of sepsis has dramatically increased in recent years, with the sepsis rate per 10,000 admissions doubling between 2000 and 2008. Moreover, in-hospital deaths are reported to be eight times greater for patients hospitalised for sepsis compared to those hospitalised with other diagnoses (17 percent and 2 percent, respectively). Compliance with evidence-based guidelines for severe sepsis and septic shock management has been shown to be low, which has been attributed to factors such as delayed recognition. Thus, a number of international campaigns (e.g., Surviving Sepsis Campaign and World Sepsis Day) have been launched to raise awareness, improve the care of patients with severe sepsis and septic shock, and emphasise early identification and intervention, which have been shown to reduce mortality. Early recognition of severe sepsis and septic shock is challenging. The complexity of the sepsis presentation makes it significantly more challenging to identify patients compared to many other time-critical conditions that are treated in the emergency department (ED), such as ST-segment elevation myocardial infarction or acute ischaemic stroke. Another challenge is ED crowding, which has been linked to the decreased likelihood of adherence to guideline-concordant care. Sepsis is a prime example of a disease in which a screening tool could significantly impact ED management. To be effective, a screening tool must cause little or no patient morbidity, be affordable and easily available, identify the conditions for which treatment exists, and be more effective when applied early in the disease course. This study, published in BMC Medical Informatics and Decision Making , aimed to determine the diagnostic accuracy of an electronic alert system in detecting severe sepsis or septic shock in ED patients. 39.2% topic match

39.0%

0.6

2013

[344] An Alarm System for Death Prediction R. Brause and E. Hanisch Int. J. Monit. Surveillance Technol. Res. 2013 - 7 citations - Show abstract - Cite 39.0% topic match

38.8%

0.9

2023

[345] Sepsis Prediction by Using a Hybrid Metaheuristic Algorithm: A Novel Approach for Optimizing Deep Neural Networks Umut Kaya, ..., and S. Aşar Diagnostics 2023 - 1 citations - Show abstract - Cite 38.8% topic match

38.4%

0.0

2014

[346] epsis mortality prediction with the Quotient Basis Kernel icent J. Ripoll, ..., and Juan Carlos Ruiz-Rodríguezc Journal Not Provided 2014 - 0 citations - Show abstract - Cite Abstract: Objective: This paper presents an algorithm to assess the risk of death in patients with sepsis. Sepsis is a common clinical syndrome in the intensive care unit (ICU) that can lead to severe sepsis, a severe state of septic shock or multi-organ failure. The proposed algorithm may be implemented as part of a clinical decision support system that can be used in combination with the scores deployed in the ICU to improve the accuracy, sensitivity and specificity of mortality prediction for patients with sepsis. Methodology: In this paper, we used the Simplified Acute Physiology Score (SAPS) for ICU patients and the Sequential Organ Failure Assessment (SOFA) to build our kernels and algorithms. In the proposed method, we embed the available data in a suitable feature space and use algorithms based on linear algebra, geometry and statistics for inference. We present a simplified version of the Fisher kernel (practical Fisher kernel for multinomial distributions), as well as a novel kernel that we named the Quotient Basis Kernel (QBK). These kernels are used as the basis for mortality prediction using soft-margin support vector machines. The two new kernels presented are compared against other generative kernels based on the Jensen–Shannon metric (centred, exponential and inverse) and other widely used kernels (linear, polynomial and Gaussian). Clinical relevance is also evaluated by comparing these results with logistic regression and the standard clinical prediction method based on the initial SAPS score. Results: As described in this paper, we tested the new methods via cross-validation with a cohort of 400 test patients. The results obtained using our methods compare favourably with those obtained using alternative kernels (80.18% accuracy for the QBK) and the standard clinical prediction method, which are based on the basal SAPS score or logistic regression (71.32% and 71.55%, respectively). The QBK presented a sensitivity and specificity of 79.34% and 83.24%, which outperformed the other kernels analysed, logistic regression and the standard clinical prediction method based on the basal SAPS score. Conclusion: Several scoring systems for patients with sepsis have been introduced and developed over the last 30 years. They allow for the assessment of the severity of disease and provide an estimate of in-hospital mortality. Physiology-based scoring systems are applied to critically ill patients and have a number of advantages over diagnosis-based systems. Severity score systems are often used to stratify critically ill patients for possible inclusion in clinical trials. In this paper, we present an effective algorithm that combines both scoring methodologies for the assessment of death in patients with sepsis that can be used to improve the sensitivity and specificity of the currently available methods. © 2014 Elsevier B.V. All rights reserved. 38.4% topic match

37.1%

0.0

2016

[347] Early warnings of heart rate deterioration. Vânia Almeida and I. Nabney Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference 2016 - 0 citations - Show abstract - Cite 37.1% topic match

36.5%

0.4

2019

[348] Using Data Analytics to Predict Hospital Mortality in Sepsis Patients Yazan Alnsour, ..., and N. Singh Int. J. Heal. Inf. Syst. Informatics 2019 - 2 citations - Show abstract - Cite 36.5% topic match

36.0%

0.0

2022

[349] Real-time sepsis prediction using fusion of on-chip analog classifier and electronic medical record Sudarsan Sadasivuni, ..., and A. Sanyal 2022 IEEE International Symposium on Circuits and Systems (ISCAS) 2022 - 0 citations - Show abstract - Cite 36.0% topic match

35.0%

0.0

2023

[350] Intelligent Medical Decision Making for Sepsis Detection using Reinforcement Learning Lakshita Singh, ..., and H. C. Taneja International Conference on Information Technology 2023 - 0 citations - Show abstract - Cite 35.0% topic match

34.2%

0.2

2012

[351] Can A Computerized Sepsis Screening And Alert System Accurately Diagnose Sepsis In Hospitalized Floor Patients And Potentially Provide Opportunities For Early Intervention? A Pilot Study Scott Zuick, ..., and B. Fuchs Asian Test Symposium 2012 - 3 citations - Show abstract - Cite Abstract: Title: Can a Computerized Sepsis Screening and Alert System Accurately Diagnose Sepsis in Hospitalized Floor Patients and Potentially Provide Opportunities for Early Intervention? A Pilot Study. Background: Sepsis Syndromes are major causes of morbidity and mortality for hospitalized patients. Several evidence-based interventions have been shown to improve outcomes but they must be instituted early to achieve better outcomes. However, early recognition of sepsis syndromes in hospitalized patients is challenging. Regrettably, SIRS is overly sensitive and not specific in the patient populations at greatest risk for developing sepsis. In addition, many hospitalized patients have baseline end-organ dysfunction, wherein subtle trends in laboratory abnormalities may escape detection. Electronic detection and alert systems offer a more focused and efficient methodology. This strategy has been deployed successfully in other aspects of critical care, e.g. in the early recognition of acute respiratory distress syndrome. We developed an electronic recognition and alert system to identify floor patients with sepsis syndromes. The objective of this study was to test the feasibility, accuracy, and potential value of a computerized sepsis screening and alert system in a large university hospital. Methods and findings: The sepsis alert used an abnormal white blood cell count coupled with a blood culture order to define sepsis. Cases were categorized as severe sepsis by meeting specified changes in laboratory tests for organ dysfunction in accordance with consensus conference criteria. Using a retrospective cohort study design, we evaluated 97 consecutive, non-intensive care unit patients who triggered a sepsis alert at a large, urban, academic medical center. The charts of the patients were reviewed and abstracted manually to determine whether sepsis was present. For confirmed sepsis cases, we determined adherence with sepsis care bundle measures, including the recognition of sepsis (using physician documentation as a proxy measure), measurement of serum lactate, administration of antibiotics, and intravenous fluid resuscitation for severe sepsis cases. Within the 97 patient cohort, 72 were confirmed to have sepsis or severe sepsis (positive predictive value of 74%). Sepsis or severe sepsis was not documented in 79%, serum lactate was not measured in 57%, antibiotics were not administered in 14% of patients with severe sepsis, and fluid boluses were not administered in 17% of patients with severe sepsis who had lactic acidosis, hypotension, and/or acute kidney injury. In patients with sepsis or severe sepsis, adherence to the complete sepsis bundle did not occur in 65%. Opportunities to improve sepsis care were more common when sepsis was not documented. Conclusion: A computerized sepsis screening and alert system designed to identify sepsis in hospitalized medical ward patients without the use of vital signs was feasible to implement and predictive for sepsis. This suggests that implementation of this system may improve the quality of sepsis care in hospitalized ward patients. 34.2% topic match

32.8%

0.9

2021

[352] Improving Septic Shock Prediction with AdaBoost and Cox Regression Model Aiman Darwiche, ..., and Sumitra Mukherjee 2021 IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE) 2021 - 3 citations - Show abstract - Cite 32.8% topic match

32.4%

1.0

2019

[353] Early Prediction of Sepsis From Clinical Data Using Single Light-GBM Model S. Chami and K. Tavakolian 2019 Computing in Cardiology (CinC) 2019 - 5 citations - Show abstract - Cite 32.4% topic match

32.2%

54.4

2015

[354] A targeted real-time early warning score (TREWScore) for septic shock K. Henry, ..., and S. Saria Science Translational Medicine 2015 - 488 citations - Show abstract - Cite Abstract: TREWScore, a targeted early warning score for septic shock, identifies patients who develop septic shock before the onset of sepsis-related organ failure. Evening the score against sepsis Sepsis is a major cause of death, which remains difficult to treat despite modern antibiotics. Early aggressive treatment of this disease improves patient mortality, but the tools currently available in the clinic do not predict who will develop sepsis and its late manifestation, septic shock, until the patients are already in advanced stages of the disease. Henry et al. used readily available data from patient monitors and medical records to develop TREWScore, a targeted real-time early warning score that predicts in advance which patients are at risk for septic shock. With a median lead time of over 24 hours, this scoring algorithm may allow clinicians enough time to intervene before the patients suffer the most damaging effects of sepsis. Sepsis is a leading cause of death in the United States, with mortality highest among patients who develop septic shock. Early aggressive treatment decreases morbidity and mortality. Although automated screening tools can detect patients currently experiencing severe sepsis and septic shock, none predict those at greatest risk of developing shock. We analyzed routinely available physiological and laboratory data from intensive care unit patients and developed “TREWScore,” a targeted real-time early warning score that predicts which patients will develop septic shock. TREWScore identified patients before the onset of septic shock with an area under the ROC (receiver operating characteristic) curve (AUC) of 0.83 [95% confidence interval (CI), 0.81 to 0.85]. At a specificity of 0.67, TREWScore achieved a sensitivity of 0.85 and identified patients a median of 28.2 [interquartile range (IQR), 10.6 to 94.2] hours before onset. Of those identified, two-thirds were identified before any sepsis-related organ dysfunction. In comparison, the Modified Early Warning Score, which has been used clinically for septic shock prediction, achieved a lower AUC of 0.73 (95% CI, 0.71 to 0.76). A routine screening protocol based on the presence of two of the systemic inflammatory response syndrome criteria, suspicion of infection, and either hypotension or hyperlactatemia achieved a lower sensitivity of 0.74 at a comparable specificity of 0.64. Continuous sampling of data from the electronic health records and calculation of TREWScore may allow clinicians to identify patients at risk for septic shock and provide earlier interventions that would prevent or mitigate the associated morbidity and mortality. 32.2% topic match

31.7%

0.9

2022

[355] Deconfounding Actor-Critic Network with Policy Adaptation for Dynamic Treatment Regimes Changchang Yin, ..., and Ping Zhang Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining 2022 - 2 citations - Show abstract - Cite - PDF 31.7% topic match

31.4%

8.7

2023

[356] Artificial intelligence in critical illness and its impact on patient care: a comprehensive review Muhammad Saqib, ..., and H. Mumtaz Frontiers in Medicine 2023 - 11 citations - Show abstract - Cite 31.4% topic match

30.1%

0.3

2018

[357] Early Prediction of Patient Mortality Based on Routine Laboratory Tests and Predictive Models in Critically Ill Patients Sven Van Poucke, ..., and M. Vukicevic Data Mining 2018 - 2 citations - Show abstract - Cite 30.1% topic match

29.7%

0.8

2021

[358] Identification of novel biomarkers for sepsis diagnosis via serum proteomic analysis using iTRAQ‐2D‐LC‐MS/MS Meng Li, ..., and Jingkun Yan Journal of Clinical Laboratory Analysis 2021 - 2 citations - Show abstract - Cite 29.7% topic match

29.6%

90.7

2021

[359] External Validation of a Widely Implemented Proprietary Sepsis Prediction Model in Hospitalized Patients. Andrew Wong, ..., and Karandeep Singh JAMA internal medicine 2021 - 281 citations - Show abstract - Cite Abstract: Importance The Epic Sepsis Model (ESM), a proprietary sepsis prediction model, is implemented at hundreds of US hospitals. The ESM's ability to identify patients with sepsis has not been adequately evaluated despite widespread use. Objective To externally validate the ESM in the prediction of sepsis and evaluate its potential clinical value compared with usual care. Design, Setting, and Participants This retrospective cohort study was conducted among 27 697 patients aged 18 years or older admitted to Michigan Medicine, the academic health system of the University of Michigan, Ann Arbor, with 38 455 hospitalizations between December 6, 2018, and October 20, 2019. Exposure The ESM score, calculated every 15 minutes. Main Outcomes and Measures Sepsis, as defined by a composite of (1) the Centers for Disease Control and Prevention surveillance criteria and (2) International Statistical Classification of Diseases and Related Health Problems, Tenth Revision diagnostic codes accompanied by 2 systemic inflammatory response syndrome criteria and 1 organ dysfunction criterion within 6 hours of one another. Model discrimination was assessed using the area under the receiver operating characteristic curve at the hospitalization level and with prediction horizons of 4, 8, 12, and 24 hours. Model calibration was evaluated with calibration plots. The potential clinical benefit associated with the ESM was assessed by evaluating the added benefit of the ESM score compared with contemporary clinical practice (based on timely administration of antibiotics). Alert fatigue was evaluated by comparing the clinical value of different alerting strategies. Results We identified 27 697 patients who had 38 455 hospitalizations (21 904 women [57%]; median age, 56 years [interquartile range, 35-69 years]) meeting inclusion criteria, of whom sepsis occurred in 2552 (7%). The ESM had a hospitalization-level area under the receiver operating characteristic curve of 0.63 (95% CI, 0.62-0.64). The ESM identified 183 of 2552 patients with sepsis (7%) who did not receive timely administration of antibiotics, highlighting the low sensitivity of the ESM in comparison with contemporary clinical practice. The ESM also did not identify 1709 patients with sepsis (67%) despite generating alerts for an ESM score of 6 or higher for 6971 of all 38 455 hospitalized patients (18%), thus creating a large burden of alert fatigue. Conclusions and Relevance This external validation cohort study suggests that the ESM has poor discrimination and calibration in predicting the onset of sepsis. The widespread adoption of the ESM despite its poor performance raises fundamental concerns about sepsis management on a national level. 29.6% topic match

29.2%

2.9

2019

[360] To catch a killer: electronic sepsis alert tools reaching a fever pitch? Halley Ruppel and V. Liu BMJ Quality & Safety 2019 - 15 citations - Show abstract - Cite 29.2% topic match

28.9%

0.4

2019

[361] Comparative Study of Light-GBM and a Combination of Survival Analysis with Deep Learning for Early Detection of Sepsis S. Chami, ..., and K. Tavakolian Journal Not Provided 2019 - 2 citations - Show abstract - Cite 28.9% topic match

28.7%

4.4

2021

[362] Atrial Fibrillation Prediction from Critically Ill Sepsis Patients S. Bashar, ..., and K. Chon Biosensors 2021 - 13 citations - Show abstract - Cite Abstract: Sepsis is defined by life-threatening organ dysfunction during infection and is the leading cause of death in hospitals. During sepsis, there is a high risk that new onset of atrial fibrillation (AF) can occur, which is associated with significant morbidity and mortality. Consequently, early prediction of AF during sepsis would allow testing of interventions in the intensive care unit (ICU) to prevent AF and its severe complications. In this paper, we present a novel automated AF prediction algorithm for critically ill sepsis patients using electrocardiogram (ECG) signals. From the heart rate signal collected from 5-min ECG, feature extraction is performed using the traditional time, frequency, and nonlinear domain methods. Moreover, variable frequency complex demodulation and tunable Q-factor wavelet-transform-based time–frequency methods are applied to extract novel features from the heart rate signal. Using a selected feature subset, several machine learning classifiers, including support vector machine (SVM) and random forest (RF), were trained using only the 2001 Computers in Cardiology data set. For testing the proposed method, 50 critically ill ICU subjects from the Medical Information Mart for Intensive Care (MIMIC) III database were used in this study. Using distinct and independent testing data from MIMIC III, the SVM achieved 80% sensitivity, 100% specificity, 90% accuracy, 100% positive predictive value, and 83.33% negative predictive value for predicting AF immediately prior to the onset of AF, while the RF achieved 88% AF prediction accuracy. When we analyzed how much in advance we can predict AF events in critically ill sepsis patients, the algorithm achieved 80% accuracy for predicting AF events 10 min early. Our algorithm outperformed a state-of-the-art method for predicting AF in ICU patients, further demonstrating the efficacy of our proposed method. The annotations of patients’ AF transition information will be made publicly available for other investigators. Our algorithm to predict AF onset is applicable for any ECG modality including patch electrodes and wearables, including Holter, loop recorder, and implantable devices. 28.7% topic match

28.4%

0.2

2019

[363] Sepsis surveillance: an examination of parameter sensitivity and alert reliability Robert C. Amland, ..., and J. Overhage JAMIA Open 2019 - 1 citations - Show abstract - Cite 28.4% topic match

28.3%

1.6

2022

[364] Preparing for the next COVID: Deep Reinforcement Learning trained Artificial Intelligence discovery of multi-modal immunomodulatory control of systemic inflammation in the absence of effective anti-microbials Dale Larie, ..., and Chase Cockrell bioRxiv 2022 - 4 citations - Show abstract - Cite Abstract: Background Despite a great deal of interest in the application of artificial intelligence (AI) to sepsis/critical illness, most current approaches are limited in their potential impact: prediction models do not (and cannot) address the lack of effective therapeutics and current approaches to enhancing the treatment of sepsis focus on optimizing the application of existing interventions, and thus cannot address the development of new treatment options/modalities. The inability to test new therapeutic applications was highlighted by the generally unsatisfactory results from drug repurposing efforts in COVID-19. Hypothesis Addressing this challenge requires the application of simulation-based, model-free deep reinforcement learning (DRL) in a fashion akin to training the game-playing AIs. We have previously demonstrated the potential of this method in the context of bacterial sepsis in which the microbial infection is responsive to antibiotic therapy. The current work addresses the control problem of multi-modal, adaptive immunomodulation in the circumstance where there is no effective anti-pathogen therapy (e.g., in a novel viral pandemic or in the face of resistant microbes). Methods This is a proof-of-concept study that determines the controllability of sepsis without the ability to pharmacologically suppress the pathogen. We use as a surrogate system a previously validated agent-based model, the Innate Immune Response Agent-based Model (IIRABM), for control discovery using DRL. The DRL algorithm ‘trains’ an AI on simulations of infection where both the control and observation spaces are limited to operating upon the defined immune mediators included in the IIRABM (a total of 11). Policies were learned using the Deep Deterministic Policy Gradient approach, with the objective function being a return to baseline system health. Results DRL trained an AI policy that improved system mortality from 85% to 10.4%. Control actions affected every one of the 11 targetable cytokines and could be divided into those with static/unchanging controls and those with variable/adaptive controls. Adaptive controls primarily targeted 3 different aspects of the immune response: 2nd order pro-inflammation governing TH1/TH2 balance, primary anti-inflammation, and inflammatory cell proliferation. Discussion The current treatment of sepsis is hampered by limitations in therapeutic options able to affect the biology of sepsis. This is heightened in circumstances where no effective antimicrobials exist, as was the case for COVID-19. Current AI methods are intrinsically unable to address this problem; doing so requires training AIs in contexts that fully represent the counterfactual space of potential treatments. The synthetic data needed for this task is only possible through the use of high-resolution, mechanism-based simulations. Finally, being able to treat sepsis will require a reorientation as to the sensing and actuating requirements needed to develop these simulations and bring them to the bedside. 28.3% topic match

28.0%

0.0

2022

[365] EARLY PREDICTION OF SEPSIS USING MACHINE LEARNING ALGORITHM: A BRIEF CLINICAL PERSPECTIVE Dr. A. A. Bardekar, ..., and Isha Upadhye EPRA International Journal of Multidisciplinary Research (IJMR) 2022 - 0 citations - Show abstract - Cite 28.0% topic match

27.7%

8.1

2021

[366] Early Prediction of Mortality, Severity, and Length of Stay in the Intensive Care Unit of Sepsis Patients Based on Sepsis 3.0 by Machine Learning Models L. Su, ..., and Y. Long Frontiers in Medicine 2021 - 25 citations - Show abstract - Cite 27.7% topic match

27.3%

0.3

2020

[367] Saving Lives With Algorithm-Enabled Process Innovation for Sepsis Care Idris Adjerid, ..., and Ö. Özer SSRN Electronic Journal 2020 - 1 citations - Show abstract - Cite Abstract: Predictive algorithms have an increasingly important role in supporting the day-to-day operations of healthcare organizations. Yet, fully realizing the value of algorithms lies critically in the opportunity to re-engineer the related processes and redefine roles in ways that make organizations more effective. We study whether and how algorithm-enabled process innovation (AEPI) creates value in the context of early diagnosis of sepsis, an infection in the bloodstream. Sepsis is a costly condition that is the leading cause of death for hospitalized patients. It is estimated that 11.0 million people died from sepsis globally in 2017. We collaborated with a large U.S. based hospital system and examined how AEPI developed for sepsis care (sepsis AEPI) impact patient mortality and related process outcomes (e.g., timely diagnosis and treatment). Our findings provide guidance for providers and policy makers. We utilize a rich set of clinical and nonclinical data in empirically examining the impact of sepsis AEPI on patient mortality and process outcomes. We leverage the staggered implementation of sepsis AEPI across hospital units and conduct our estimation on a carefully matched sample. The matching utilizes data on patient vitals and the logic behind the algorithm to create a robust comparison group consisting of patient visits for which sepsis AEPI would have triggered an alert if it had been in place. Our empirical analysis shows that sepsis AEPI reduces the likelihood of death from sepsis (43% relative reduction in mortality risk due to sepsis). This reduction occurs in parallel with a 21% relative improvement in the likelihood of timely diagnostic (lactate measurement) and clinical interventions (antibiotics administration) for sepsis patients. We identify lapses in process outcomes in parallel to a lapse in AEPI's propensity to reduce sepsis-related mortality over extended periods of implementation. Our findings suggest that streamlining sepsis care processes through a predictive algorithm (i.e., algorithm-based monitoring of real-time patient data and providing predictions, streamlined communication channels for coordinating care for a patient with sepsis prediction, and a more standardized process for sepsis diagnosis and treatment) holds significant promise in reducing the loss of life from sepsis. We show that such value, however, requires adherence to process changes even after the algorithm becomes a routine part of the day-to-day operations of the hospital. 27.3% topic match

26.7%

2.7

2021

[368] A Simulated Prospective Evaluation of a Deep Learning Model for Real-Time Prediction of Clinical Deterioration Among Ward Patients* P. Shah, ..., and G. Weissman Critical Care Medicine 2021 - 9 citations - Show abstract - Cite Abstract: Supplemental Digital Content is available in the text. OBJECTIVES: The National Early Warning Score, Modified Early Warning Score, and quick Sepsis-related Organ Failure Assessment can predict clinical deterioration. These scores exhibit only moderate performance and are often evaluated using aggregated measures over time. A simulated prospective validation strategy that assesses multiple predictions per patient-day would provide the best pragmatic evaluation. We developed a deep recurrent neural network deterioration model and conducted a simulated prospective evaluation. DESIGN: Retrospective cohort study. SETTING: Four hospitals in Pennsylvania. PATIENTS: Inpatient adults discharged between July 1, 2017, and June 30, 2019. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: We trained a deep recurrent neural network and logistic regression model using data from electronic health records to predict hourly the 24-hour composite outcome of transfer to ICU or death. We analyzed 146,446 hospitalizations with 16.75 million patient-hours. The hourly event rate was 1.6% (12,842 transfers or deaths, corresponding to 260,295 patient-hours within the predictive horizon). On a hold-out dataset, the deep recurrent neural network achieved an area under the precision-recall curve of 0.042 (95% CI, 0.04–0.043), comparable with logistic regression model (0.043; 95% CI 0.041 to 0.045), and outperformed National Early Warning Score (0.034; 95% CI, 0.032–0.035), Modified Early Warning Score (0.028; 95% CI, 0.027– 0.03), and quick Sepsis-related Organ Failure Assessment (0.021; 95% CI, 0.021–0.022). For a fixed sensitivity of 50%, the deep recurrent neural network achieved a positive predictive value of 3.4% (95% CI, 3.4–3.5) and outperformed logistic regression model (3.1%; 95% CI 3.1–3.2), National Early Warning Score (2.0%; 95% CI, 2.0–2.0), Modified Early Warning Score (1.5%; 95% CI, 1.5–1.5), and quick Sepsis-related Organ Failure Assessment (1.5%; 95% CI, 1.5–1.5). CONCLUSIONS: Commonly used early warning scores for clinical decompensation, along with a logistic regression model and a deep recurrent neural network model, show very poor performance characteristics when assessed using a simulated prospective validation. None of these models may be suitable for real-time deployment. 26.7% topic match

26.6%

0.0

2016

[369] Early warnings of heart rate deterioration. In 2016 38th Annual Conference of the Engineering I. Nabney Journal Not Provided 2016 - 0 citations - Show abstract - Cite 26.6% topic match

25.7%

0.8

2018

[370] SMITH : Smart Medical Information Technology for Healthcare No author found Journal Not Provided 2018 - 5 citations - Show abstract - Cite 25.7% topic match

24.3%

6.5

2020

[371] Neonatal Sepsis Diagnosis Decision-Making Based on Artificial Neural Networks A. Helguera-Repetto, ..., and C. Irles Frontiers in Pediatrics 2020 - 25 citations - Show abstract - Cite 24.3% topic match

23.9%

0.2

2019

[372] Performance comparison of prediction models for neonatal sepsis using logistic regression, multiple discriminant analysis and artificial neural network Jyoti Thakur, ..., and Roop Pahuja Biomedical Physics & Engineering Express 2019 - 1 citations - Show abstract - Cite 23.9% topic match

23.1%

0.0

2018

[373] Early Detection of Sepsis Induced Deterioration with First 48-hour ECG, Plethysmograph, and Respiratory Rate Biosignals Using Machine Learning Models Francesco Dal Canton Journal Not Provided 2018 - 0 citations - Show abstract - Cite 23.1% topic match

22.5%

0.0

2024

[374] Assessment of Sepsis Risk at Admission to the Emergency Department: Clinical Interpretable Prediction Model Umran Aygun, ..., and L. P. Ardigò Diagnostics 2024 - 0 citations - Show abstract - Cite 22.5% topic match

22.5%

0.0

2018

[375] 1431: ADULTS WITH SEPTIC SHOCK AND EXTREME HYPERFERRITINEMIA EXHIBIT PATHOGENIC IMMUNE VARIATION K. Kernan, ..., and J. Carcillo Critical Care Medicine 2018 - 0 citations - Show abstract - Cite Abstract: Critical Care Medicine • Volume 46 • Number 1 (Supplement) www.ccmjournal.org Learning Objectives: Severe sepsis is a leading cause of death in the United States and costs health care systems up to $20 billion annually. Methods have been developed to electronically monitor patients for severe sepsis, but few have provided predictive capabilities to enable early intervention. We hypothesize, patient length of stay (LOS) and in-hospital mortality rate decrease with the use of a machine learning-based severe sepsis prediction algorithm in the intensive care unit. Methods: A randomized clinical trial was conducted at two mixed medical-surgical intensive care units at UCSF from December 2016 to February 2017. This factorial, open label trial was designed to test whether InSight®, a machine learning-based severe sepsis prediction algorithm, was better than the current Electronic Health Record (EHR)-based severe sepsis detection system. All adult patients (18+) admitted to the participating units were eligible for study. Enrolled patients were automatically assigned to a trial arm according to a random allocation sequence. Participants randomized to the experimental group were screened by InSight and the existing severe sepsis detection method. Using only the most commonly recorded measurements in the electronic health record, primarily vital signs and age, Insight predicted sepsis onset and alerted the appropriate care team. Upon receiving an alert from the prediction algorithm, the care team evaluated the patient for severe sepsis and initiated the severe sepsis bundle, if appropriate. The primary outcome was LOS. The secondary outcome was in-hospital mortality rate. Results: Outcomes (75 control patients, 67 experimental) were analyzed. There was a significant (P = .04) decrease in hospital LOS (13 d vs. 10.3 d) and a 58.0% reduction in in-hospital mortality rate when using Insight (21.3% vs 8.96%), (P = .02). No adverse events were reported during this trial. Conclusions: A machine learning-based sepsis prediction tool may improve patient outcomes and decrease sepsis-related costs. 22.5% topic match

22.1%

5.4

2017

[376] Predictors of mortality of severe sepsis among adult patients in the medical Intensive Care Unit A. Mohamed, ..., and P. James Lung India : Official Organ of Indian Chest Society 2017 - 38 citations - Show abstract - Cite 22.1% topic match

22.1%

0.0

2021

[377] Detection of Sepsis Patients Using Biomarkers Based on Machine Learning Mahsa Eskandari, ..., and Salar Mohammadi https://doi.org/10.21203/rs.3.rs-769430/v1 2021 - 0 citations - Show abstract - Cite 22.1% topic match

22.0%

1.4

2020

[378] Optimizing Medical Treatment for Sepsis in Intensive Care: from Reinforcement Learning to Pre-Trial Evaluation Luchen Li, ..., and Aldo A. Faisal ArXiv 2020 - 6 citations - Show abstract - Cite - PDF 22.0% topic match

21.8%

4.8

2020

[379] Predicting Progression to Septic Shock in the Emergency Department using an Externally Generalizable Machine Learning Algorithm G. Wardi, ..., and S. Nemati medRxiv : the preprint server for health sciences 2020 - 18 citations - Show abstract - Cite 21.8% topic match

21.8%

0.3

2021

[380] Proximity of Cellular and Physiological Response Failures in Sepsis A. Jazayeri, ..., and Christopher C. Yang IEEE Journal of Biomedical and Health Informatics 2021 - 1 citations - Show abstract - Cite 21.8% topic match

21.2%

0.6

2022

[381] 7 Healthcare staff perceptions on using artificial intelligence predictive tools: a qualitative study N. Hassan, ..., and S. Slight Part I: ePapers 2022 - 1 citations - Show abstract - Cite Abstract: ObjectiveArtificial intelligence (AI) predictive tools can help inform the clinical decision-making process by, for example, detecting early signs of patient deterioration or predicting the likelihood of a patient developing a particular disease or complications postsurgery. However, it is unclear how acceptable or useful clinicians find these tools in practice. This project aims to explore healthcare staff’ perceptions on the benefits and challenges of using AI tools to inform clinical decision-making in practice.MethodsHealthcare staff (physicians, pharmacists and nurses) working in different departments at one large teaching hospital in the North East were invited to participate in semi-structured interviews. Interviews were conducted between August and November 2021 by zoom videoconferencing, with questions focused on what AI predictive tools they currently use, how they guide daily tasks around diagnosis, management, prevention, prognosis and screening, and what challenges they face with their use. All transcribed files were checked for accuracy. Thematic saturation guided the volume of qualitative data collection. Qualitative data analysis and development of themes was performed for each interview using Nvivo 12 software. Ethical approval was obtained (20/EM/0183, IRAS 280077).ResultsTen healthcare staff were interviewed (physicians (n=7), pharmacists (n=1), surgeons (n=2)) from different medical specialities (e.g., Oncology, Endocrinology, Cardiology, Head and Neck, and transplant surgery). Five themes emerged, including the meaning of the term AI, the usefulness of AI predictive tools in informing clinical decision-making, features that healthcare staff found helpful, and challenges around their use. Healthcare staff recognised the benefits of AI predictive tools in being able to ‘detect deterioration quicker than you would currently do’(05-ID), which informed decisions around patient discharge: ‘can you safely send them home (...) or do you want to keep them, in case they do deteriorate’ (05-ID). They found AI predictive tools useful when explaining the potential risk of cardiovascular events to patients and encouraging medication adherence ‘it does help so much convincing the patient to actually adhere to the medication’ (07-Endo).During COVID-19, AI prediction tools helped identify patients that might potentially need mechanical ventilation and ICU admission. Healthcare staff also felt it was important that AI predictive tools provided reliable information, that was easy to understand, and integrated with the current systems. A concern raised around the use of AI predictive tools was whether they might ‘mislead junior doctors or doctors who would not have that much of a clinical sense and would totally depend on it’ (07-Endo).ConclusionThis study demonstrated opportunities for the application of AI predictive tools in clinical practice. Concerns raised around the use of these tools should be considered by developers. We recognise that the perceptions of only a small number of clinicians were included mainly due to the increased time pressures on staff during the COVID-19 pandemic. Healthcare staff described essential features that will guide the future development of AI predictive tools with higher potential for application in real practice. 21.2% topic match

20.5%

1.4

2012

[382] A Bayesian network for early diagnosis of sepsis patients: a basis for a clinical decision support system E. Gultepe, ..., and I. Tagkopoulos 2012 IEEE 2nd International Conference on Computational Advances in Bio and medical Sciences (ICCABS) 2012 - 18 citations - Show abstract - Cite 20.5% topic match

20.0%

4.6

2018

[383] Prediction of Sepsis and In-Hospital Mortality Using Electronic Health Records A. Khojandi, ..., and William Paiva Methods of Information in Medicine 2018 - 27 citations - Show abstract - Cite 20.0% topic match

19.8%

1.2

2019

[384] Identifying Optimal Features from Heart Rate Variability for Early Detection of Sepsis in Pediatric Intensive Care P. Amiri, ..., and M. Mirzaaghayan 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) 2019 - 6 citations - Show abstract - Cite 19.8% topic match

19.6%

0.0

2022

[385] Detection of sepsis during emergency department triage using machine learning Oleksandr Ivanov, ..., and Christian Reilly Journal Not Provided 2022 - 0 citations - Show abstract - Cite - PDF 19.6% topic match

18.8%

29.3

2019

[386] A Machine Learning Algorithm to Predict Severe Sepsis and Septic Shock: Development, Implementation, and Impact on Clinical Practice. MD Heather M. Giannini, ..., and MD Craig A. Umscheid Critical Care Medicine 2019 - 146 citations - Show abstract - Cite 18.8% topic match

18.7%

8.2

2017

[387] Heart rate variability as predictor of mortality in sepsis: A prospective cohort study F. M. de Castilho, ..., and M. D. de Sousa PLoS ONE 2017 - 58 citations - Show abstract - Cite Abstract: Background Sepsis is a serious medical condition with increasing prevalence and high mortality. The role of the autonomic nervous system in pathophysiology of sepsis has been increasingly researched. The objective of this study is to evaluate the Heart rate variability (HRV) as a predictor of mortality in septic patients. Methods This was a prospective cohort of patients diagnosed with sepsis. Patient recruitment was carried out at ICU in tertiary university hospital between March 2012 and February 2014. Clinical data and laboratory exams were collected at admission. Each patient underwent a 20-minute Holter and a 24-hour Holter on the first day of enrollment. The primary outcome was the 28-day all-cause mortality. Results A total of 63 patients were included. Patients were categorized into nonsurvivor group (n = 16) or survivor group (n = 47) depending on this endpoint. Survivors were younger (48.6 years vs. 63.0 years), had better renal function and lower values in severity scores (APACHE II and SOFA) compared to nonsurvivors. In the 20-minute Holter, SDNN, Total Power, VLF Power, LF Power and LF/HF of nonsurvivors were significantly lower than those of survivors (p = <0.001, p = 0.003, p = 0.002, p = 0.006, p = 0.009 respectively). ROC curve of SDNN was built, showing area under the curve of 0.772 (0.638–0.906) for mortality. The value of 17ms was chosen as best SDNN cutoff to discriminate survivors and nonsurvivors. In the Cox proportional regression, adjusted for SOFA score and for APACHE II, a SDNN ≤ 17ms was associated with a greater risk of death, with hazard ratios of 6.3 (1.4–28.0; p = 0.015) and 5.5 (1,2–24,8; p = 0.027), respectively. The addition of the dichotomized SDNN to the SOFA model reduced AIC and increased the concordance statistic and the R2, indicating that predictive power of the SDNN + SOFA model is better than predictive power of SOFA only. Conclusions Several HRV parameters are reduced in nonsurviving septic patients. SDNN ≤17 is a risk factor for death in septic patients, even after adjusting for severity scores. 18.7% topic match

18.5%

5.4

2019

[388] Critical Care, Critical Data C. Cosgriff, ..., and David J. Stone Biomedical Engineering and Computational Biology 2019 - 30 citations - Show abstract - Cite 18.5% topic match

18.0%

1.7

2022

[389] A Conservative Q-Learning approach for handling distribution shift in sepsis treatment strategies Pramod S. Kaushik, ..., and R. Bapi ArXiv 2022 - 4 citations - Show abstract - Cite - PDF 18.0% topic match

17.8%

0.6

2022

[390] A Deep Reinforcement Computation Model for Sepsis Treatment Hang Yu and Qingchen Zhang 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) 2022 - 1 citations - Show abstract - Cite 17.8% topic match

17.5%

0.8

2022

[391] Accurate detection of sepsis at ED triage using machine learning with clinical natural language processing Oleksandr Ivanov, ..., and Christian Reilly ArXiv 2022 - 2 citations - Show abstract - Cite 17.5% topic match

17.3%

0.8

2020

[392] A Time-Critical Topic Model for Predicting the Survival Time of Sepsis Patients Wenping Guo, ..., and Xue Li Sci. Program. 2020 - 3 citations - Show abstract - Cite 17.3% topic match

17.0%

0.0

2021

[393] Assessment of Sepsis in the ICU by Linear and Complex Characterization of Cardiovascular Dynamics Maximiliano Mollura, ..., and R. Barbieri 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) 2021 - 0 citations - Show abstract - Cite 17.0% topic match

16.6%

0.5

2020

[394] [Artificial intelligence provides promotion of big data in medical work and contribution to people's health as soon as possible: real-time warning of critical illness is the pioneer of artificial intelligence in clinical medicine]. Di-fen Wang and Di Liu Zhonghua wei zhong bing ji jiu yi xue 2020 - 2 citations - Show abstract - Cite 16.6% topic match

16.6%

0.7

2017

[395] Assessment of Nursing Response to a Real-Time Alerting Tool for Sepsis: A Provider Survey. Kristen E. Miller, ..., and R. Arnold American journal of hospital medicine 2017 - 5 citations - Show abstract - Cite 16.6% topic match

16.5%

0.4

2022

[396] Desired Characteristics of a Clinical Decision Support System for Early Sepsis Recognition: Interview Study Among Hospital-Based Clinicians J. Silvestri, ..., and G. Weissman JMIR Human Factors 2022 - 1 citations - Show abstract - Cite Abstract: Background Sepsis is a major burden for health care systems in the United States, with over 750,000 cases annually and a total cost of approximately US $20 billion. The hallmark of sepsis treatment is early and appropriate initiation of antibiotic therapy. Although sepsis clinical decision support (CDS) systems can provide clinicians with early predictions of suspected sepsis or imminent clinical decline, such systems have not reliably demonstrated improvements in clinical outcomes or care processes. Growing evidence suggests that the challenges of integrating sepsis CDS systems into clinical workflows, gaining the trust of clinicians, and making sepsis CDS systems clinically relevant at the bedside are all obstacles to successful deployment. However, there are significant knowledge gaps regarding the achievement of these implementation and deployment goals. Objective We aimed to identify perceptions of predictive information in sepsis CDS systems based on clinicians’ past experiences, explore clinicians’ perceptions of a hypothetical sepsis CDS system, and identify the characteristics of a CDS system that would be helpful in promoting timely recognition and management of suspected sepsis in a multidisciplinary, team-based clinical setting. Methods We conducted semistructured interviews with practicing bedside nurses, advanced practice providers, and physicians at a large academic medical center between September 2020 and March 2021. We used modified human factor methods (contextual interview and cognitive walkthrough performed over video calls because of the COVID-19 pandemic) and conducted a thematic analysis using an abductive approach for coding to identify important patterns and concepts in the interview transcripts. Results We interviewed 6 bedside nurses and 9 clinicians responsible for ordering antibiotics (advanced practice providers or physicians) who had a median of 4 (IQR 4-6.5) years of experience working in an inpatient setting. We then synthesized critical content from the thematic analysis of the data into four domains: clinician perceptions of prediction models and alerts; previous experiences of clinician encounters with predictive information and risk scores; desired characteristics of a CDS system build, including predictions, supporting information, and delivery methods for a potential alert; and the clinical relevance and potential utility of a CDS system. These 4 domains were strongly linked to clinicians’ perceptions of the likelihood of adoption and the impact on clinical workflows when diagnosing and managing patients with suspected sepsis. Ultimately, clinicians desired a trusted and actionable CDS system to improve sepsis care. Conclusions Building a trusted and actionable sepsis CDS alert is paramount to achieving acceptability and use among clinicians. These findings can inform the development, implementation, and deployment strategies for CDS systems that support the early detection and treatment of sepsis. This study also highlights several key opportunities when eliciting clinician input before the development and deployment of prediction models. 16.5% topic match

16.5%

2.4

2023

[397] Identifying Predictors Associated with Risk of Death or Admission to Intensive Care Unit in Internal Medicine Patients with Sepsis: A Comparison of Statistical Models and Machine Learning Algorithms A. Mirijello, ..., and d’Angelo Antibiotics 2023 - 3 citations - Show abstract - Cite Abstract: Background: Sepsis is a time-dependent disease: the early recognition of patients at risk for poor outcome is mandatory. Aim: To identify prognostic predictors of the risk of death or admission to intensive care units in a consecutive sample of septic patients, comparing different statistical models and machine learning algorithms. Methods: Retrospective study including 148 patients discharged from an Italian internal medicine unit with a diagnosis of sepsis/septic shock and microbiological identification. Results: Of the total, 37 (25.0%) patients reached the composite outcome. The sequential organ failure assessment (SOFA) score at admission (odds ratio (OR): 1.83; 95% confidence interval (CI): 1.41–2.39; p < 0.001), delta SOFA (OR: 1.64; 95% CI: 1.28–2.10; p < 0.001), and the alert, verbal, pain, unresponsive (AVPU) status (OR: 5.96; 95% CI: 2.13–16.67; p < 0.001) were identified through the multivariable logistic model as independent predictors of the composite outcome. The area under the receiver operating characteristic curve (AUC) was 0.894; 95% CI: 0.840–0.948. In addition, different statistical models and machine learning algorithms identified further predictive variables: delta quick-SOFA, delta-procalcitonin, mortality in emergency department sepsis, mean arterial pressure, and the Glasgow Coma Scale. The cross-validated multivariable logistic model with the least absolute shrinkage and selection operator (LASSO) penalty identified 5 predictors; and recursive partitioning and regression tree (RPART) identified 4 predictors with higher AUC (0.915 and 0.917, respectively); the random forest (RF) approach, including all evaluated variables, obtained the highest AUC (0.978). All models’ results were well calibrated. Conclusions: Although structurally different, each model identified similar predictive covariates. The classical multivariable logistic regression model was the most parsimonious and calibrated one, while RPART was the easiest to interpret clinically. Finally, LASSO and RF were the costliest in terms of number of variables identified. 16.5% topic match

15.9%

0.9

2023

[398] Biomarkers for surgical sepsis. A review of foreign scientific and medical publications Sergey G. Sсherbak, ..., and T. A. Kamilova Journal of Clinical Practice 2023 - 1 citations - Show abstract - Cite 15.9% topic match

15.6%

0.0

2023

[399] Investigating the Role of Machine Learning Algorithms in Predicting Sepsis using Vital Sign Data Amit Sundas, ..., and Ashraf Osman Ibrahim International Journal of Advanced Computer Science and Applications 2023 - 0 citations - Show abstract - Cite 15.6% topic match

15.3%

1.5

2021

[400] Enhancement in Performance of Septic Shock Prediction Using National Early Warning Score, Initial Triage Information, and Machine Learning Analysis. Hyoungju Yun, ..., and Sukwha Kim The Journal of emergency medicine 2021 - 5 citations - Show abstract - Cite 15.3% topic match

15.2%

0.0

2022

[401] Application of Artificial Intelligence in Early–Stage Diagnosis of Sepsis Oznur Esra Par, ..., and H. Sever Proceedings of the 2022 5th Artificial Intelligence and Cloud Computing Conference 2022 - 0 citations - Show abstract - Cite 15.2% topic match

15.0%

1.9

2022

[402] A Reinforcement Learning Application for Optimal Fluid and Vasopressor Interventions in Septic ICU Patients Maximiliano Mollura, ..., and Riccardo Barbieri 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) 2022 - 4 citations - Show abstract - Cite 15.0% topic match

14.3%

0.0

2022

[403] Developing an Interpretable Machine Learning Model to Predict In-Hospital Mortality in Sepsis Patients: A Retrospective Study of MIMIC-IV Shuhe Li, ..., and C. Cai https://doi.org/10.21203/rs.3.rs-1282305/v1 2022 - 0 citations - Show abstract - Cite Abstract: Background: Risk stratification plays an essential role in the decision-making of sepsis management, whereas neither a single serum biomarker nor traditional scoring tools can satisfy the need to assess this heterogeneous population comprehensively. The study intended to develop an interpretable machine learning model for predicting in-hospital mortality in critically ill patients with sepsis. Methods: Adult patients fulfilling the definition of Sepsis-3 were included in the Medical Information Mart for Intensive Care (MIMIC)-IV database. Relevant clinical features were extracted within the first 24 hours in ICU, and missing data were analyzed and imputed. We randomly separated the dataset into train and test sub-cohort by the ratio of 7:3, then an outcome-balanced train dataset was synthesized for model training. Extreme gradient boosting (XGBoost) was employed when feature selection and hyperparameter tuning were performed afterward. The fine-tuned XGBoost model was then compared with stepwise logistic regression (LR) and established severity scores. Eventually, we inspected the interpretability of the new model using XGBoost feature importance and Shapley Additive exPlanations (SHAP) plot. Results: The final cohort had 24,573 patients, of which 3,785 patients died during hospitalization (15.4%). Ten iterations of multiple imputations were executed to fill missing data in all 91 incomplete variables. Subsequently, 10,572 patients formed the balanced dataset used for training. The XGBoost model showed greater discrimination than stepwise LR and severity scores such as Simplified Acute Physiology Score (SAPS)-III score (AUC: 0.849, 95% CI: 0.8386-0.8599; AUC: 0.618, 95% CI: 0.3927-0.8437; AUC: 0.803, 95% CI: 0.7898-0.8165 respectively). Based on model interpretation, some decisive factors, including elevated lactate and anion gap level, prolonged partial thromboplastin time, decreased urine volume, were greatly correlated with poor survival outcomes in sepsis. Conclusions: In the field of predicting the mortality risk of sepsis patients in hospitals, the XGBoost-based model demonstrated superior performance to stepwise LR and other scores. In addition, the model exhibited good interpretability and might provide valuable hints on future directions of clinical practice and research. 14.3% topic match

14.0%

0.0

2022

[404] 1169. Derivation And Validation of an International Clinical Prognostication Model for 28-day Sepsis Mortality. P. Blair, ..., and D. Clark Open Forum Infectious Diseases 2022 - 0 citations - Show abstract - Cite Abstract: Abstract Background Survival prediction models have largely been derived and validated only in high-resource Western countries or in single center studies. We sought to create a prediction model for 28-day mortality using laboratory and physiologic parameters from 3 international sepsis cohorts and externally validated the model. Methods During 2014 to 2021, adult hospitalized patients with suspected infection were enrolled in Durham, United States (N=180) and those with suspected infection and ≥2 SIRS (Systemic Inflammatory Response Syndrome) criteria in Takeo, Cambodia (N=200), and Kumasi, Ghana (N=187). Twenty-five clinical laboratory and physiologic parameters were candidate covariates and sepsis screening scores included as comparators. First, bivariate Cox regression models were performed to determine risk of individual parameters. Then, a 10-fold cross-validated forward stepwise model selection technique was used to eliminate nonsignificant variables using a p-value < 0.10 and the cross-validated C-statistic was estimated. Lastly, this model was applied to an external cohort of hospitalized adults with suspected infection and ≥2 SIRS in Fort Portal, Uganda (N=331 with 9.3% 28-day mortality). Results Among 567 participants, overall mortality was 16.4% at 28-days. Mortality rate highest in Ghana (31.0%), followed by Cambodia (11.0%) and the United States (7.2%). Bivariate analyses identified hypernatremia ( >145 mEq/L) being associated with the highest risk of death (hazard ratio: 7.42; 95% CI: 3.65 to 15.10; Figure 1). On multivariable analysis, a 28-day mortality model including mean arterial pressure, Glasgow Coma score, blood sodium, lactate, and blood urea nitrogen (Table 1) resulted in a 10-fold cross-validated C-statistic of 0.80 (95% CI: 0.61 to 0.88). This model predicted mortality accurately in the validation cohort with a C-statistic of 0.74 (95%CI: 0.69 to 0.79). Figure 1. Forest plot for bivariate analyses for one month survival across United States, Cambodia, and Ghana cohorts. Conclusion Hypotension, altered mental status, serum sodium, serum BUN, and plasma lactate accurately identified risk of death by 28-days among those with suspected sepsis in 3 international derivation cohorts and in a validation cohort in Uganda. Our findings emphasize the importance of clinical laboratory results for sepsis risk stratification. Disclosures Ephraim L. Tsalik, MD PhD, Danaher Diagnostics, Predigen, and Biomeme: In the past 3 years, I have had held equity and consulted for Predigen and Biomeme. Currently, I am an employee of Danaher Diagnostics. Christopher W. Woods, MD MPH, Predigen, Inc: Co-founder. 14.0% topic match

13.7%

2.0

2023

[405] Developing an Interpretable Machine Learning Model to Predict in-Hospital Mortality in Sepsis Patients: A Retrospective Temporal Validation Study Shuhe Li, ..., and C. Cai Journal of Clinical Medicine 2023 - 3 citations - Show abstract - Cite 13.7% topic match

13.7%

1.8

2024

[406] Transformative Potential of AI in Healthcare: Definitions, Applications, and Navigating the Ethical Landscape and Public Perspectives Molly Bekbolatova, ..., and Milan Toma Healthcare 2024 - 1 citations - Show abstract - Cite 13.7% topic match

13.6%

9.7

2020

[407] A Machine Learning-Based Prediction of Hospital Mortality in Patients With Postoperative Sepsis R. Yao, ..., and Yong-ming Yao Frontiers in Medicine 2020 - 43 citations - Show abstract - Cite 13.6% topic match

13.4%

1.3

2023

[408] Detection of sepsis using biomarkers based on machine learning. Mahsa Eskandari, ..., and Salar Mohammadi Bratislavske lekarske listy 2023 - 2 citations - Show abstract - Cite 13.4% topic match

13.2%

0.3

2021

[409] Unsupervised learning approach for understanding critical infectious disease progression in ICU patients Guilherme Brites Ramos Journal Not Provided 2021 - 1 citations - Show abstract - Cite 13.2% topic match

13.0%

None

[410] Early recognition of sepsis at the emergency department Titus A. P. de Hond https://doi.org/10.33540/1828 None - 0 citations - Show abstract - Cite 13.0% topic match

13.0%

3.9

2014

[411] Septic Shock Prediction for Patients with Missing Data Joyce Ho, ..., and Joydeep Ghosh ACM Trans. Manag. Inf. Syst. 2014 - 40 citations - Show abstract - Cite 13.0% topic match

12.9%

3.6

2021

[412] Heart rate n-variability (HRnV) measures for prediction of mortality in sepsis patients presenting at the emergency department Nan Liu, ..., and M. Ong PLoS ONE 2021 - 13 citations - Show abstract - Cite Abstract: Background: Sepsis is a potentially life threatening condition that requires prompt recognition and treatment for optimal outcomes. There is little consensus on an objective way to assess for sepsis severity and risk for mortality. In recent years, heart rate variability (HRV), a measure of the cardiac autonomic regulation derived from short electrocardiogram tracings, has been found to correlate with sepsis mortality, and its use as a prognostic variable and for risk stratification has been promising. In this paper, we present using novel heart rate n-variability (HRnV) measures for sepsis mortality risk prediction and compare against current mortality prediction scores. Methods: This study was a retrospective cohort study on a convenience sample of patients presenting to the emergency department (ED) of Singapore General Hospital between September 2014 to April 2017. Patients were included in the study if they were above 21 years old, were suspected to have sepsis by their attending physician, triaged as emergency or urgent cases, and if they met two or more of the Systemic Inflammatory Response Syndrome (SIRS) criteria. Demographic and clinical variables were obtained from the electronic medical records, and HRV and novel HRnV parameters were calculated from five minute ECG tracings. Univariable analysis was conducted on variables obtained, with the primary outcome being 30-day in-hospital mortality (IHM). Variables selected through univariable analysis and stepwise selection were included in a multivariable logistic regression model, the results of which were presented using receiver operating curve (ROC) analysis. Results: Of 342 patients included for final analysis, 66 (19%) met with the primary outcome. On univariable analysis, 85 out of 142 analysed HRV and HRnV parameters showed statistical difference between groups. The final multivariable logistic regression model comprised of 21 variables including four vital signs, two HRV parameters, and 15 HRnV parameters. The area under the curve (AUC) of the model was 0.86 (95% confidence interval 0.81-0.90), outperforming several established clinical scores. Conclusion: The use of novel HRnV measures can provide adequate power to predictive models in the risk stratification of patients presenting to the ED with sepsis. When included in a multivariable logistic regression model, the HRnV-based model outperformed traditional risk stratification scoring systems. The HRnV measures may have potential to allow for a rapid, objective, and accurate means of patient risk stratification for sepsis severity and mortality. 12.9% topic match

12.7%

1.1

2013

[413] Early Diagnosis and Its Benefits in Sepsis Blood Purification Treatment Mohamed F. Ghalwash, ..., and Z. Obradovic 2013 IEEE International Conference on Healthcare Informatics 2013 - 12 citations - Show abstract - Cite 12.7% topic match

12.6%

2.9

2022

[414] Implementation of Machine Learning Pipelines for Clinical Practice: Development and Validation Study L. Kanbar, ..., and J. Dexheimer JMIR Medical Informatics 2022 - 7 citations - Show abstract - Cite 12.6% topic match

12.5%

0.0

2020

[415] Translational Study Tracking Dynamic Changes in Cardiac Pattern Variability and Systemic Inflammation in Critically Ill Patients S. Tackett, ..., and F. Jacono The FASEB Journal 2020 - 0 citations - Show abstract - Cite Abstract: Sepsis is a dynamic complex condition with high patient mortality and health‐care system cost for which the understanding of underlying pathophysiology is still evolving. We hypothesize that pattern variability of centrally controlled physiological rhythms, like cardiac and respiratory rhythms, decreases with an increase in systemic inflammation, such as sepsis. In our lab, we have previously demonstrated in an animal sepsis model that respiratory pattern predictability will increase with disease onset and progression. We describe a complementary IRB approved clinical study, in which physiological waveform data were recorded continuously from consented adult patients (n=43 to date) admitted to the medical intensive care unit (MICU). Serum was collected at intervals determined clinically and subsequently quantified using Luminex assays. The electrocardiogram data was analyzed for heart rate variability (HRV) indices, including Coefficient of Variation, Poincare Plots and Power Spectral Density (high frequency power (HFP)) for the hour preceding and succeeding each serum sampling. Of the 15 patients analyzed, we identified 18 intervals between successive blood draws with a significant change in IL‐6 serum concentration, defined as a 20% relative change accompanied by >20 pg/mL absolute change. In each of the 6 time intervals where IL‐6 was significantly increased there was an associated decrease in HRV and/or HFP. In 12 time intervals IL‐6 decreased; 7 of these were associated with an increase in HRV and/or HFP. Previous studies and our own studies on humans and rats conclude that decreases in the variability, or increases in the predictability, of physiological rhythms correlate to diseased state. Our working hypothesis is that neural inflammation in the brainstem alters central regulation of cardio‐respiratory rhythms and their coupling. As sepsis has had consistent and widespread negative impact on patients, the heath‐care system, and healthcare economy, it is imperative to identify and describe biometrics that serve as early warnings to clinicians. 12.5% topic match

12.0%

0.6

2016

[416] Using demographic and time series physiological features to classify sepsis in the intensive care unit K. Gunnarsdottir, ..., and S. Sarma 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) 2016 - 5 citations - Show abstract - Cite 12.0% topic match

12.0%

1.9

2021

[417] Prediction of 90-Day Mortality among Sepsis Patients Based on a Nomogram Integrating Diverse Clinical Indices Qingjin Zeng, ..., and Jingchun Song BioMed Research International 2021 - 6 citations - Show abstract - Cite 12.0% topic match

11.7%

1.9

2022

[418] Interpretable Machine Learning to Optimize Early In-Hospital Mortality Prediction for Elderly Patients with Sepsis: A Discovery Study Xiaowei Ke, ..., and Aimin Wang Computational and Mathematical Methods in Medicine 2022 - 3 citations - Show abstract - Cite Abstract: Sepsis-related mortality rates are high among elderly patients, especially those in intensive care units (ICUs). Early prediction of the prognosis of sepsis is critical, as prompt and effective treatment can improve prognosis. Researchers have predicted mortality and the development of sepsis using machine learning algorithms; however, few studies specifically focus on elderly patients with sepsis. This paper proposes a viable model for early prediction of in-hospital mortality among elderly patients diagnosed with sepsis. We extracted patient information from the Medical Information Mart for Intensive Care IV database. We employed several machine learning algorithms to predict the in-hospital mortality of elderly ICU patients with sepsis. The performance of the model was evaluated by using the AUROC and F1 score. Furthermore, the SHAP algorithm was used to explain the model, analyze how the individual features affect the model output, and visualize the Shapley value for a single individual. Our study included 18522 elderly patients, with a mortality of 15.4%. After screening, 59 clinical variables were extracted to develop models. Feature importance analysis showed that age, PO2, RDW, SPO2, WBC, and urine output were significantly related to the in-hospital mortality. According to the results of AUROC (0.871 (95% CI: 0.854–0.888)) and F1 score (0.547 (95% CI: 0.539–0.661)) analyses, the extreme gradient boosting (XGBoost) model outperformed the other models (i.e., LGBM, LR, RF, DT, and KNN). Furthermore, SHAP force analysis illustrated how the constructed model visualized the individualized prediction of death. XGBoost machine learning framework gives good in-hospital mortality prediction of elderly patients with sepsis and can maximize prediction model accuracy. The XGBoost model could be an effective tool to assist doctors in identifying high-risk cases of in-hospital mortality among elderly patients with sepsis. This could be used to create a clinical decision support system in the future. 11.7% topic match

11.4%

5.9

2024

[419] Impact of a deep learning sepsis prediction model on quality of care and survival Aaron Boussina, ..., and G. Wardi NPJ Digital Medicine 2024 - 3 citations - Show abstract - Cite 11.4% topic match

11.1%

6.0

2018

[420] Recent Temporal Pattern Mining for Septic Shock Early Prediction Farzaneh Khoshnevisan, ..., and Min Chi 2018 IEEE International Conference on Healthcare Informatics (ICHI) 2018 - 37 citations - Show abstract - Cite 11.1% topic match

11.1%

0.0

2019

[421] Study of spectrum of sepsis and prediction of its outcome in patients admitted to ICU using different scoring systems K. Ravi, ..., and K. A. Rao International Journal of Advances in Medicine 2019 - 0 citations - Show abstract - Cite 11.1% topic match

10.8%

5.6

2020

[422] Artificial intelligence and computer simulation models in critical illness A. Lal, ..., and B. Pickering World Journal of Critical Care Medicine 2020 - 23 citations - Show abstract - Cite 10.8% topic match

10.2%

0.0

2023

[423] The Use of AI in Predicting Patient Outcomes and Deterioration in the Emergency Department Amal Akeel, ..., and Talal Abu Suliman JOURNAL OF HEALTHCARE SCIENCES 2023 - 0 citations - Show abstract - Cite 10.2% topic match

10.2%

1.9

2021

[424] Prediction of Impending Septic Shock in Children With Sepsis Ran Liu, ..., and R. Winslow Critical Care Explorations 2021 - 6 citations - Show abstract - Cite Abstract: Supplemental Digital Content is available in the text. Objectives: Sepsis and septic shock are leading causes of in-hospital mortality. Timely treatment is crucial in improving patient outcome, yet treatment delays remain common. Early prediction of those patients with sepsis who will progress to its most severe form, septic shock, can increase the actionable window for interventions. We aim to extend a time-evolving risk score, previously developed in adult patients, to predict pediatric sepsis patients who are likely to develop septic shock before its onset, and to determine whether or not these risk scores stratify into groups with distinct temporal evolution once this prediction is made. Design: Retrospective cohort study. Setting: Academic medical center from July 1, 2016, to December 11, 2020. Patients: Six-thousand one-hundred sixty-one patients under 18 admitted to the Johns Hopkins Hospital PICU. Interventions: None. Measurements and Main Results: We trained risk models to predict impending transition into septic shock and compute time-evolving risk scores representative of a patient’s probability of developing septic shock. We obtain early prediction performance of 0.90 area under the receiver operating curve, 43% overall positive predictive value, patient-specific positive predictive value as high as 62%, and an 8.9-hour median early warning time using Sepsis-3 labels based on age-adjusted Sequential Organ Failure Assessment score. Using spectral clustering, we stratified pediatric sepsis patients into two clusters differing in septic shock prevalence, mortality, and proportion of patients adequately fluid resuscitated. CONCLUSIONS: We demonstrate the applicability of our methodology for early prediction and stratification for risk of septic shock in pediatric sepsis patients. Through analyses of risk score evolution over time, we corroborate our past finding of an abrupt transition preceding onset of septic shock in children and are able to stratify pediatric sepsis patients using their risk score trajectories into low and high-risk categories. 10.2% topic match

10.1%

0.0

2022

[425] Fair Reinforcement Learning for Maternal Sepsis Treatment S. Carey, ..., and M. de Kamps medRxiv 2022 - 0 citations - Show abstract - Cite 10.1% topic match

10.0%

0.4

2019

[426] Sepsis Onset Prediction Applying a Stacked Combination of a Recurrent Neural Network and a Gradient Boosted Machine Matthieu Scherpf, ..., and F. Gräßer 2019 Computing in Cardiology (CinC) 2019 - 2 citations - Show abstract - Cite 10.0% topic match

9.9%

3.2

2023

[427] Vital sign‐based detection of sepsis in neonates using machine learning Antoine Honoré, ..., and E. Herlenius Acta Paediatrica 2023 - 5 citations - Show abstract - Cite 9.9% topic match

9.9%

0.6

2022

[428] Expectations of Anesthesiology and Intensive Care Professionals Toward Artificial Intelligence: Observational Study J. Kloka, ..., and Benjamin Friedrichson JMIR Formative Research 2022 - 1 citations - Show abstract - Cite Abstract: Background Artificial intelligence (AI) applications offer numerous opportunities to improve health care. To be used in the intensive care unit, AI must meet the needs of staff, and potential barriers must be addressed through joint action by all stakeholders. It is thus critical to assess the needs and concerns of anesthesiologists and intensive care physicians related to AI in health care throughout Europe. Objective This Europe-wide, cross-sectional observational study investigates how potential users of AI systems in anesthesiology and intensive care assess the opportunities and risks of the new technology. The web-based questionnaire was based on the established analytic model of acceptance of innovations by Rogers to record 5 stages of innovation acceptance. Methods The questionnaire was sent twice in 2 months (March 11, 2021, and November 5, 2021) through the European Society of Anaesthesiology and Intensive Care (ESAIC) member email distribution list. A total of 9294 ESAIC members were reached, of whom 728 filled out the questionnaire (response rate 728/9294, 8%). Due to missing data, 27 questionnaires were excluded. The analyses were conducted with 701 participants. Results A total of 701 questionnaires (female: n=299, 42%) were analyzed. Overall, 265 (37.8%) of the participants have been in contact with AI and evaluated the benefits of this technology higher (mean 3.22, SD 0.39) than participants who stated no previous contact (mean 3.01, SD 0.48). Physicians see the most benefits of AI application in early warning systems (335/701, 48% strongly agreed, and 358/701, 51% agreed). Major potential disadvantages were technical problems (236/701, 34% strongly agreed, and 410/701, 58% agreed) and handling difficulties (126/701, 18% strongly agreed, and 462/701, 66% agreed), both of which could be addressed by Europe-wide digitalization and education. In addition, the lack of a secure legal basis for the research and use of medical AI in the European Union leads doctors to expect problems with legal liability (186/701, 27% strongly agreed, and 374/701, 53% agreed) and data protection (148/701, 21% strongly agreed, and 343/701, 49% agreed). Conclusions Anesthesiologists and intensive care personnel are open to AI applications in their professional field and expect numerous benefits for staff and patients. Regional differences in the digitalization of the private sector are not reflected in the acceptance of AI among health care professionals. Physicians anticipate technical difficulties and lack a stable legal basis for the use of AI. Training for medical staff could increase the benefits of AI in professional medicine. Therefore, we suggest that the development and implementation of AI in health care require a solid technical, legal, and ethical basis, as well as adequate education and training of users. 9.9% topic match

9.4%

0.0

2000

[429] Technical note Clinical decision-support systems for intensive care units using case-based reasoning M. Frize and R. Walker Journal Not Provided 2000 - 1 citations - Show abstract - Cite 9.4% topic match

9.4%

2.4

2022

[430] Value of Neutrophil:Lymphocyte Ratio Combined with Sequential Organ Failure Assessment Score in Assessing the Prognosis of Sepsis Patients Yixuan Li, ..., and Xinghua Ye International Journal of General Medicine 2022 - 6 citations - Show abstract - Cite 9.4% topic match

9.3%

0.4

2020

[431] Machine Learning Based Analysis of Sepsis: Review Mehanas Shahul 2020 International Conference on Emerging Trends in Information Technology and Engineering (ic-ETITE) 2020 - 2 citations - Show abstract - Cite 9.3% topic match

9.2%

0.9

2023

[432] Artificial Intelligence in the Intensive Care Unit: Present and Future in the COVID-19 Era M. Kołodziejczak, ..., and Piotr Kowalski Journal of Personalized Medicine 2023 - 1 citations - Show abstract - Cite 9.2% topic match

9.2%

5.8

2012

[433] Monitoring and Identification of Sepsis Development through a Composite Measure of Heart Rate Variability A. Bravi, ..., and A. Seely PLoS ONE 2012 - 69 citations - Show abstract - Cite 9.2% topic match

9.1%

1.4

2023

[434] Model-interpreted outcomes of artificial neural networks classifying immune biomarkers associated with severe infections in ICU Gustavo Sganzerla Martinez, ..., and D. Kelvin Frontiers in Immunology 2023 - 2 citations - Show abstract - Cite 9.1% topic match

9.0%

0.3

2017

[435] Adaptive Artificial Intelligence for Inpatient Monitoring and Healthcare Management Gijare Ca, ..., and Deshp BioChemistry: An Indian Journal 2017 - 2 citations - Show abstract - Cite 9.0% topic match

8.8%

0.4

2021

[436] Application of Deep Learning Technology in Predicting the Risk of Inpatient Death in Intensive Care Unit Ming Li, ..., and HuaJuan Xu Journal of Healthcare Engineering 2021 - 1 citations - Show abstract - Cite 8.8% topic match

8.7%

0.0

2023

[437] 1423. A Simple Electronic Medical Record-Based Predictors of Illness Severity in Sepsis (SEPSIS) Score Alex Cressman, ..., and D. MacFadden Open Forum Infectious Diseases 2023 - 0 citations - Show abstract - Cite Abstract: Abstract Background Current scores for predicting sepsis outcomes are limited by generalizability, complexity, and electronic medical record (EMR) integration. Here, we validate a simple EMR-based score for sepsis outcomes in a large multi-centre cohort. Methods A simple electronic medical record-based predictor of illness severity in sepsis (SEPSIS) score was developed (4 additive lab-based predictors: Creatinine, Bilirubin, Platelet Count, Lactate) using a retrospective cohort study of patients admitted to internal medicine services from April 2010 - March 2015, across four hospitals in Toronto, Canada. We identified patients with sepsis based upon receipt of antibiotics and positive (non-screening) cultures on admission. Chart review was conducted to extract components of qSOFA and NEWS2 scores. The primary outcome was in-hospital mortality and secondary outcomes were ICU admission at 72 hours, and hospital length of stay (LOS). We calculated the area under the receiver operating curve (AUROC) for the SEPSIS score, qSOFA, and NEWS2. We then evaluated the SEPSIS score in a contemporary cohort (2015 to 2019) of patients receiving systemic antibiotics. Results Our initial cohort included 1,890 patients with a median age of 72 years (IQR: 56-83). 9% of the cohort died during hospitalization, 13% were admitted to ICU at 72 hours, and mean LOS was 12.7 days (SD: 21.5). In the initial and the contemporary (2015-2019, 4811 patients) cohorts, the AUROCs of the SEPSIS score for predicting in-hospital mortality were 0.63 and 0.64 respectively, which were similar to NEWS2 (0.62 and 0.67) and qSOFA (0.62 and 0.68). AUROCs for predicting ICU admission at 72 hours, and length of stay >14 days, were similar between scores, in the initial and contemporary cohorts. All scores were generally well calibrated for predicting mortality (Figure 1).Figure 1. Mortality risk by predictor score (low, medium, high) and score type. Conclusion The EMR-based SEPSIS score shows a similar ability to predict important clinical outcomes compared with other validated scores (qSOFA and NEWS2). Because of the SEPSIS score’s simplicity, it may prove a useful tool for clinical and research applications. Disclosures All Authors: No reported disclosures 8.7% topic match

8.7%

1.8

2022

[438] Reduced oxygen saturation entropy is associated with poor prognosis in critically ill patients with sepsis Margaret Gheorghita, ..., and A. Mani Physiological Reports 2022 - 3 citations - Show abstract - Cite 8.7% topic match

8.6%

1.6

2023

[439] Crossing the AI Chasm in Neurocritical Care M. Cascella, ..., and E. Bignami Comput. 2023 - 2 citations - Show abstract - Cite 8.6% topic match

8.5%

2.3

2022

[440] Predicting the Mortality of ICU Patients by Topic Model with Machine-Learning Techniques Chih-Chou Chiu, ..., and J. T. Qiu Healthcare 2022 - 5 citations - Show abstract - Cite 8.5% topic match

8.3%

5.2

2018

[441] Development and External Validation of an Automated Computer-Aided Risk Score for Predicting Sepsis in Emergency Medical Admissions Using the Patient’s First Electronically Recorded Vital Signs and Blood Test Results* M. Faisal, ..., and M. Mohammed Critical Care Medicine 2018 - 33 citations - Show abstract - Cite Abstract: Objectives: To develop a logistic regression model to predict the risk of sepsis following emergency medical admission using the patient’s first, routinely collected, electronically recorded vital signs and blood test results and to validate this novel computer-aided risk of sepsis model, using data from another hospital. Design: Cross-sectional model development and external validation study reporting the C-statistic based on a validated optimized algorithm to identify sepsis and severe sepsis (including septic shock) from administrative hospital databases using International Classification of Diseases, 10th Edition, codes. Setting: Two acute hospitals (York Hospital - development data; Northern Lincolnshire and Goole Hospital - external validation data). Patients: Adult emergency medical admissions discharged over a 24-month period with vital signs and blood test results recorded at admission. Interventions: None. Main Results: The prevalence of sepsis and severe sepsis was lower in York Hospital (18.5% = 4,861/2,6247; 5.3% = 1,387/2,6247) than Northern Lincolnshire and Goole Hospital (25.1% = 7,773/30,996; 9.2% = 2,864/30,996). The mortality for sepsis (York Hospital: 14.5% = 704/4,861; Northern Lincolnshire and Goole Hospital: 11.6% = 899/7,773) was lower than the mortality for severe sepsis (York Hospital: 29.0% = 402/1,387; Northern Lincolnshire and Goole Hospital: 21.4% = 612/2,864). The C-statistic for computer-aided risk of sepsis in York Hospital (all sepsis 0.78; sepsis: 0.73; severe sepsis: 0.80) was similar in an external hospital setting (Northern Lincolnshire and Goole Hospital: all sepsis 0.79; sepsis: 0.70; severe sepsis: 0.81). A cutoff value of 0.2 gives reasonable performance. Conclusions: We have developed a novel, externally validated computer-aided risk of sepsis, with reasonably good performance for estimating the risk of sepsis for emergency medical admissions using the patient’s first, electronically recorded, vital signs and blood tests results. Since computer-aided risk of sepsis places no additional data collection burden on clinicians and is automated, it may now be carefully introduced and evaluated in hospitals with sufficient informatics infrastructure. 8.3% topic match

8.2%

23.3

2019

[442] Development and Evaluation of a Machine Learning Model for the Early Identification of Patients at Risk for Sepsis Ryan J. Delahanty, ..., and Spencer S. Jones Annals of Emergency Medicine 2019 - 129 citations - Show abstract - Cite 8.2% topic match

8.1%

0.1

2016

[443] [PREDICTION OF LATE ONSET SEPSIS IN VERY LOW BIRTH WEIGHT INFANTS BY A SOFTWARE APPLICATION--ARE WE THERE YET?]. Z. Ergaz, ..., and B. Bar‐Oz Harefuah 2016 - 1 citations - Show abstract - Cite 8.1% topic match

8.1%

1.5

2016

[444] Optimization of sepsis risk assessment for ward patients S. Mitchell, ..., and Laura E. Barnes 2016 IEEE Systems and Information Engineering Design Symposium (SIEDS) 2016 - 12 citations - Show abstract - Cite 8.1% topic match

8.0%

37.0

2021

[445] Artificial intelligence in sepsis early prediction and diagnosis using unstructured data in healthcare K. Goh, ..., and G. Tan Nature Communications 2021 - 129 citations - Show abstract - Cite 8.0% topic match

8.0%

1.4

1994

[446] Intelligent systems in patient monitoring and therapy management. A survey of research projects. S. Uckun International journal of clinical monitoring and computing 1994 - 42 citations - Show abstract - Cite 8.0% topic match

8.0%

5.3

2018

[447] Automated monitoring compared to standard care for the early detection of sepsis in critically ill patients. S. Warttig, ..., and Andrew F. Smith The Cochrane database of systematic reviews 2018 - 32 citations - Show abstract - Cite Abstract: BACKGROUND Sepsis is a life-threatening condition that is usually diagnosed when a patient has a suspected or documented infection, and meets two or more criteria for systemic inflammatory response syndrome (SIRS). The incidence of sepsis is higher among people admitted to critical care settings such as the intensive care unit (ICU) than among people in other settings. If left untreated sepsis can quickly worsen; severe sepsis has a mortality rate of 40% or higher, depending on definition. Recognition of sepsis can be challenging as it usually requires patient data to be combined from multiple unconnected sources, and interpreted correctly, which can be complex and time consuming to do. Electronic systems that are designed to connect information sources together, and automatically collate, analyse, and continuously monitor the information, as well as alerting healthcare staff when pre-determined diagnostic thresholds are met, may offer benefits by facilitating earlier recognition of sepsis and faster initiation of treatment, such as antimicrobial therapy, fluid resuscitation, inotropes, and vasopressors if appropriate. However, there is the possibility that electronic, automated systems do not offer benefits, or even cause harm. This might happen if the systems are unable to correctly detect sepsis (meaning that treatment is not started when it should be, or it is started when it shouldn't be), or healthcare staff may not respond to alerts quickly enough, or get 'alarm fatigue' especially if the alarms go off frequently or give too many false alarms. OBJECTIVES To evaluate whether automated systems for the early detection of sepsis can reduce the time to appropriate treatment (such as initiation of antibiotics, fluids, inotropes, and vasopressors) and improve clinical outcomes in critically ill patients in the ICU. SEARCH METHODS We searched CENTRAL; MEDLINE; Embase; CINAHL; ISI Web of science; and LILACS, clinicaltrials.gov, and the World Health Organization trials portal. We searched all databases from their date of inception to 18 September 2017, with no restriction on country or language of publication. SELECTION CRITERIA We included randomized controlled trials (RCTs) that compared automated sepsis-monitoring systems to standard care (such as paper-based systems) in participants of any age admitted to intensive or critical care units for critical illness. We defined an automated system as any process capable of screening patient records or data (one or more systems) automatically at intervals for markers or characteristics that are indicative of sepsis. We defined critical illness as including, but not limited to postsurgery, trauma, stroke, myocardial infarction, arrhythmia, burns, and hypovolaemic or haemorrhagic shock. We excluded non-randomized studies, quasi-randomized studies, and cross-over studies . We also excluded studies including people already diagnosed with sepsis. DATA COLLECTION AND ANALYSIS We used the standard methodological procedures expected by Cochrane. Our primary outcomes were: time to initiation of antimicrobial therapy; time to initiation of fluid resuscitation; and 30-day mortality. Secondary outcomes included: length of stay in ICU; failed detection of sepsis; and quality of life. We used GRADE to assess the quality of evidence for each outcome. MAIN RESULTS We included three RCTs in this review. It was unclear if the RCTs were three separate studies involving 1199 participants in total, or if they were reports from the same study involving fewer participants. We decided to treat the studies separately, as we were unable to make contact with the study authors to clarify.All three RCTs are of very low study quality because of issues with unclear randomization methods, allocation concealment and uncertainty of effect size. Some of the studies were reported as abstracts only and contained limited data, which prevented meaningful analysis and assessment of potential biases.The studies included participants who all received automated electronic monitoring during their hospital stay. Participants were randomized to an intervention group (automated alerts sent from the system) or to usual care (no automated alerts sent from the system).Evidence from all three studies reported 'Time to initiation of antimicrobial therapy'. We were unable to pool the data, but the largest study involving 680 participants reported median time to initiation of antimicrobial therapy in the intervention group of 5.6 hours (interquartile range (IQR) 2.3 to 19.7) in the intervention group (n = not stated) and 7.8 hours (IQR 2.5 to 33.1) in the control group (n = not stated).No studies reported 'Time to initiation of fluid resuscitation' or the adverse event 'Mortality at 30 days'. However very low-quality evidence was available where mortality was reported at other time points. One study involving 77 participants reported 14-day mortality of 20% in the intervention group and 21% in the control group (numerator and denominator not stated). One study involving 442 participants reported mortality at 28 days, or discharge was 14% in the intervention group and 10% in the control group (numerator and denominator not reported). Sample sizes were not reported adequately for these outcomes and so we could not estimate confidence intervals.Very low-quality evidence from one study involving 442 participants reported 'Length of stay in ICU'. Median length of stay was 3.0 days in the intervention group (IQR = 2.0 to 5.0), and 3.0 days (IQR 2.0 to 4.0 in the control).Very low-quality evidence from one study involving at least 442 participants reported the adverse effect 'Failed detection of sepsis'. Data were only reported for failed detection of sepsis in two participants and it wasn't clear which group(s) this outcome occurred in.No studies reported 'Quality of life'. AUTHORS' CONCLUSIONS It is unclear what effect automated systems for monitoring sepsis have on any of the outcomes included in this review. Very low-quality evidence is only available on automated alerts, which is only one component of automated monitoring systems. It is uncertain whether such systems can replace regular, careful review of the patient's condition by experienced healthcare staff. 8.0% topic match

7.7%

9.1

2022

[448] Predicting clinical outcomes using artificial intelligence and machine learning in neonatal intensive care units: a systematic review R. McAdams, ..., and Harpreet Singh Journal of Perinatology 2022 - 20 citations - Show abstract - Cite 7.7% topic match

7.3%

2.9

2021

[449] Point-of-critical-care diagnostics for sepsis enabled by multiplexed micro and nanosensing technologies. Brandon K. Ashley and U. Hassan Wiley interdisciplinary reviews. Nanomedicine and nanobiotechnology 2021 - 10 citations - Show abstract - Cite 7.3% topic match

7.3%

6.0

2019

[450] Deep Inverse Reinforcement Learning for Sepsis Treatment Chao Yu, ..., and Jiming Liu 2019 IEEE International Conference on Healthcare Informatics (ICHI) 2019 - 31 citations - Show abstract - Cite 7.3% topic match

7.0%

1.0

2020

[451] Pathophysiologic Signatures of Bloodstream Infection in Critically Ill Adults Alex N. Zimmet, ..., and C. Moore Critical Care Explorations 2020 - 4 citations - Show abstract - Cite 7.0% topic match

6.9%

17.7

2019

[452] Machine learning models for early sepsis recognition in the neonatal intensive care unit using readily available electronic health record data A. Masino, ..., and R. Grundmeier PLoS ONE 2019 - 96 citations - Show abstract - Cite Abstract: Background Rapid antibiotic administration is known to improve sepsis outcomes, however early diagnosis remains challenging due to complex presentation. Our objective was to develop a model using readily available electronic health record (EHR) data capable of recognizing infant sepsis at least 4 hours prior to clinical recognition. Methods and findings We performed a retrospective case control study of infants hospitalized ≥48 hours in the Neonatal Intensive Care Unit (NICU) at the Children’s Hospital of Philadelphia between September 2014 and November 2017 who received at least one sepsis evaluation before 12 months of age. We considered two evaluation outcomes as cases: culture positive–positive blood culture for a known pathogen (110 evaluations); and clinically positive–negative cultures but antibiotics administered for ≥120 hours (265 evaluations). Case data was taken from the 44-hour window ending 4 hours prior to evaluation. We randomly sampled 1,100 44-hour windows of control data from all times ≥10 days removed from any evaluation. Model inputs consisted of up to 36 features derived from routine EHR data. Using 10-fold nested cross-validation, 8 machine learning models were trained to classify inputs as sepsis positive or negative. When tasked with discriminating culture positive cases from controls, 6 models achieved a mean area under the receiver operating characteristic (AUC) between 0.80–0.82 with no significant differences between them. Including both culture and clinically positive cases, the same 6 models achieved an AUC between 0.85–0.87, again with no significant differences. Conclusions Machine learning models can identify infants with sepsis in the NICU hours prior to clinical recognition. Learning curves indicate model improvement may be achieved with additional training examples. Additional input features may also improve performance. Further research is warranted to assess potential performance improvements and clinical efficacy in a prospective trial. 6.9% topic match

6.8%

0.0

2023

[453] Identification of potential diagnostic and prognostic biomarkers for sepsis based on machine learning. Li Ke, ..., and Zhiyong Peng Computational and structural biotechnology journal 2023 - 0 citations - Show abstract - Cite 6.8% topic match

6.8%

0.0

2022

[454] Improving the Timeliness of Early Prediction Models for Sepsis through Utility Optimization Anastasios Lamproudis, ..., and P. Nauclér 2022 IEEE 34th International Conference on Tools with Artificial Intelligence (ICTAI) 2022 - 0 citations - Show abstract - Cite 6.8% topic match

6.7%

1.1

2021

[455] A REVIEW ANALYSIS ON THE POTENTIAL FOR ARTIFICIAL INTELLIGENCE IN HEALTHCARE No author found Journal Not Provided 2021 - 4 citations - Show abstract - Cite 6.7% topic match

6.5%

12.8

2020

[456] Improvements in Patient Monitoring in the Intensive Care Unit: Survey Study A. Poncette, ..., and F. Balzer Journal of Medical Internet Research 2020 - 54 citations - Show abstract - Cite Abstract: Background Due to demographic change and, more recently, coronavirus disease (COVID-19), the importance of modern intensive care units (ICU) is becoming apparent. One of the key components of an ICU is the continuous monitoring of patients' vital parameters. However, existing advances in informatics, signal processing, or engineering that could alleviate the burden on ICUs have not yet been applied. This could be due to the lack of user involvement in research and development. Objective This study focused on the satisfaction of ICU staff with current patient monitoring and their suggestions for future improvements. We aimed to identify aspects of monitoring that interrupt patient care, display devices for remote monitoring, use cases for artificial intelligence (AI), and whether ICU staff members are willing to improve their digital literacy or contribute to the improvement of patient monitoring. We further aimed to identify differences in the responses of different professional groups. Methods This survey study was performed with ICU staff from 4 ICUs of a German university hospital between November 2019 and January 2020. We developed a web-based 36-item survey questionnaire, by analyzing a preceding qualitative interview study with ICU staff, about the clinical requirements of future patient monitoring. Statistical analyses of questionnaire results included median values with their bootstrapped 95% confidence intervals, and chi-square tests to compare the distributions of item responses of the professional groups. Results In total, 86 of the 270 ICU physicians and nurses completed the survey questionnaire. The majority stated they felt confident using the patient monitoring equipment, but that high rates of false-positive alarms and the many sensor cables interrupted patient care. Regarding future improvements, respondents asked for wireless sensors, a reduction in the number of false-positive alarms, and hospital standard operating procedures for alarm management. Responses to the display devices proposed for remote patient monitoring were divided. Most respondents indicated it would be useful for earlier alerting or when they were responsible for multiple wards. AI for ICUs would be useful for early detection of complications and an increased risk of mortality; in addition, the AI could propose guidelines for therapy and diagnostics. Transparency, interoperability, usability, and staff training were essential to promote the use of AI. The majority wanted to learn more about new technologies for the ICU and required more time for learning. Physicians had fewer reservations than nurses about AI-based intelligent alarm management and using mobile phones for remote monitoring. Conclusions This survey study of ICU staff revealed key improvements for patient monitoring in intensive care medicine. Hospital providers and medical device manufacturers should focus on reducing false alarms, implementing hospital alarm standard operating procedures, introducing wireless sensors, preparing for the use of AI, and enhancing the digital literacy of ICU staff. Our results may contribute to the user-centered transfer of digital technologies into practice to alleviate challenges in intensive care medicine. Trial Registration ClinicalTrials.gov NCT03514173; https://clinicaltrials.gov/ct2/show/NCT03514173 6.5% topic match

6.5%

1.9

2016

[457] Validation of test performance and clinical time zero for an electronic health record embedded severe sepsis alert N. L. Downing, ..., and J. Rolnick Applied Clinical Informatics 2016 - 16 citations - Show abstract - Cite 6.5% topic match

6.5%

0.8

2019

[458] On Computer-Aided Prognosis of Septic Shock from Vital Signs Hasan Oğul, ..., and Ricardo Colomo Palacios 2019 IEEE 32nd International Symposium on Computer-Based Medical Systems (CBMS) 2019 - 4 citations - Show abstract - Cite 6.5% topic match

6.4%

None

[459] БИОМАРКЕРЫ ХИРУРГИЧЕСКОГО СЕПСИСА. ОБЗОР ЗАРУБЕЖНЫХ НАУЧНО-МЕДИЦИНСКИХ ПУБЛИКАЦИЙ No author found Journal Not Provided None - 0 citations - Show abstract - Cite 6.4% topic match

6.4%

0.6

2019

[460] Network-Based Modeling of Sepsis: Quantification and Evaluation of Simultaneity of Organ Dysfunctions A. Jazayeri, ..., and R. Arnold Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics 2019 - 3 citations - Show abstract - Cite 6.4% topic match

6.2%

0.0

2023

[461] Risk Factors for Pediatric Sepsis in the Emergency Department Laura Y. Mercurio, ..., and C. Eickhoff Pediatric Emergency Care 2023 - 0 citations - Show abstract - Cite Abstract: Objective To identify underappreciated sepsis risk factors among children presenting to a pediatric emergency department (ED). Methods A retrospective observational study (2017–2019) of children aged 18 years and younger presenting to a pediatric ED at a tertiary care children's hospital with fever, hypotension, or an infectious disease International Classification of Diseases (ICD)-10 diagnosis. Structured patient data including demographics, problem list, and vital signs were extracted for 35,074 qualifying ED encounters. According to the Improving Pediatric Sepsis Outcomes Classification, confirmed by expert review, 191 patients met clinical sepsis criteria. Five machine learning models were trained to predict sepsis/nonsepsis outcomes. Top features enabling model performance (N = 20) were then extracted to identify patient risk factors. Results Machine learning methods reached a performance of up to 93% sensitivity and 84% specificity in identifying patients who received a hospital diagnosis of sepsis. A random forest classifier performed the best, followed by a classification and regression tree. Maximum documented heart rate was the top feature in these models, with importance coefficients (ICs) of 0.09 and 0.21, which represent how much an individual feature contributes to the model. Maximum mean arterial pressure was the second most important feature (IC 0.05, 0.13). Immunization status (IC 0.02), age (IC 0.03), and patient zip code (IC 0.02) were also among the top features enabling models to predict sepsis from ED visit data. Stratified analysis revealed changes in the predictive importance of risk factors by race, ethnicity, oncologic history, and insurance status. Conclusions Machine learning models trained to identify pediatric sepsis using ED clinical and sociodemographic variables confirmed well-established predictors, including heart rate and mean arterial pressure, and identified underappreciated relationships between sepsis and patient age, immunization status, and demographics. 6.2% topic match

6.1%

0.0

2015

[462] Recognizing and managing sepsis: what needs to be done? article openly available. Please share how this access benefits you. Your story matters D. Yealy, ..., and T. Nutbeam Journal Not Provided 2015 - 0 citations - Show abstract - Cite 6.1% topic match

6.0%

12.3

2020

[463] The role of artificial intelligence in management of critical COVID-19 patients S. Rahmatizadeh, ..., and A. Dabbagh https://doi.org/10.22037/JCMA.V5I1.29752 2020 - 53 citations - Show abstract - Cite 6.0% topic match

5.9%

16.9

2017

[464] An Improved Multi-Output Gaussian Process RNN with Real-Time Validation for Early Sepsis Detection Joseph D. Futoma, ..., and Cara O'Brien Machine Learning in Health Care 2017 - 117 citations - Show abstract - Cite - PDF 5.9% topic match

5.9%

0.9

2019

[465] The early prediction of neonates mortality in Intensive Care Unit Z. Kefi, ..., and M. Naceur 2019 International Conference on Advanced Systems and Emergent Technologies (IC_ASET) 2019 - 5 citations - Show abstract - Cite 5.9% topic match

5.8%

0.4

2022

[466] Sepsis Prediction for the General Ward Setting Sean C. Yu, ..., and A. Michelson Frontiers in Digital Health 2022 - 1 citations - Show abstract - Cite 5.8% topic match

5.7%

2.4

2020

[467] Enhancing sepsis management through machine learning techniques: A review. N. Ocampo-Quintero, ..., and D. Glez-Peña Medicina intensiva 2020 - 10 citations - Show abstract - Cite 5.7% topic match

5.7%

2.2

2023

[468] A Methodology for a Scalable, Collaborative, and Resource-Efficient Platform, MERLIN, to Facilitate Healthcare AI Research Raphael Cohen and V. Kovacheva IEEE Journal of Biomedical and Health Informatics 2023 - 3 citations - Show abstract - Cite 5.7% topic match

5.7%

16.6

2017

[469] Early sepsis detection in critical care patients using multiscale blood pressure and heart rate dynamics. S. Shashikumar, ..., and S. Nemati Journal of electrocardiology 2017 - 112 citations - Show abstract - Cite 5.7% topic match

5.6%

0.8

2022

[470] Improving Sepsis Prediction Model Generalization With Optimal Transport Jie Wang, ..., and Rishikesan Kamaleswaran Journal Not Provided 2022 - 2 citations - Show abstract - Cite 5.6% topic match

5.5%

7.0

2021

[471] Prediction of Late-Onset Sepsis in Preterm Infants Using Monitoring Signals and Machine Learning Laura Cabrera-Quirós, ..., and C. van Pul Critical Care Explorations 2021 - 25 citations - Show abstract - Cite Abstract: Supplemental Digital Content is available in the text. Objectives: Prediction of late-onset sepsis (onset beyond day 3 of life) in preterm infants, based on multiple patient monitoring signals 24 hours before onset. Design: Continuous high-resolution electrocardiogram and respiration (chest impedance) data from the monitoring signals were extracted and used to create time-interval features representing heart rate variability, respiration, and body motion. For each infant with a blood culture-proven late-onset sepsis, a Cultures, Resuscitation, and Antibiotics Started Here moment was defined. The Cultures, Resuscitation, and Antibiotics Started Here moment served as an anchor point for the prediction analysis. In the group with controls (C), an “equivalent crash moment” was calculated as anchor point, based on comparable gestational and postnatal age. Three common machine learning approaches (logistic regressor, naive Bayes, and nearest mean classifier) were used to binary classify samples of late-onset sepsis from C. For training and evaluation of the three classifiers, a leave-k-subjects-out cross-validation was used. Setting: Level III neonatal ICU. Patients: The patient population consisted of 32 premature infants with sepsis and 32 age-matched control patients. Interventions: No interventions were performed. Measurements and Main Results: For the interval features representing heart rate variability, respiration, and body motion, differences between late-onset sepsis and C were visible up to 5 hours preceding the Cultures, Resuscitation, and Antibiotics Started Here moment. Using a combination of all features, classification of late-onset sepsis and C showed a mean accuracy of 0.79 ± 0.12 and mean precision rate of 0.82 ± 0.18 3 hours before the onset of sepsis. Conclusions: Information from routine patient monitoring can be used to predict sepsis. Specifically, this study shows that a combination of electrocardiogram-based, respiration-based, and motion-based features enables the prediction of late-onset sepsis hours before the clinical crash moment. 5.5% topic match

5.4%

8.4

2021

[472] The Promise of AI in Detection, Diagnosis, and Epidemiology for Combating COVID-19: Beyond the Hype M. Abdulkareem and S. Petersen Frontiers in Artificial Intelligence 2021 - 27 citations - Show abstract - Cite Abstract: COVID-19 has created enormous suffering, affecting lives, and causing deaths. The ease with which this type of coronavirus can spread has exposed weaknesses of many healthcare systems around the world. Since its emergence, many governments, research communities, commercial enterprises, and other institutions and stakeholders around the world have been fighting in various ways to curb the spread of the disease. Science and technology have helped in the implementation of policies of many governments that are directed toward mitigating the impacts of the pandemic and in diagnosing and providing care for the disease. Recent technological tools, artificial intelligence (AI) tools in particular, have also been explored to track the spread of the coronavirus, identify patients with high mortality risk and diagnose patients for the disease. In this paper, areas where AI techniques are being used in the detection, diagnosis and epidemiological predictions, forecasting and social control for combating COVID-19 are discussed, highlighting areas of successful applications and underscoring issues that need to be addressed to achieve significant progress in battling COVID-19 and future pandemics. Several AI systems have been developed for diagnosing COVID-19 using medical imaging modalities such as chest CT and X-ray images. These AI systems mainly differ in their choices of the algorithms for image segmentation, classification and disease diagnosis. Other AI-based systems have focused on predicting mortality rate, long-term patient hospitalization and patient outcomes for COVID-19. AI has huge potential in the battle against the COVID-19 pandemic but successful practical deployments of these AI-based tools have so far been limited due to challenges such as limited data accessibility, the need for external evaluation of AI models, the lack of awareness of AI experts of the regulatory landscape governing the deployment of AI tools in healthcare, the need for clinicians and other experts to work with AI experts in a multidisciplinary context and the need to address public concerns over data collection, privacy, and protection. Having a dedicated team with expertise in medical data collection, privacy, access and sharing, using federated learning whereby AI scientists hand over training algorithms to the healthcare institutions to train models locally, and taking full advantage of biomedical data stored in biobanks can alleviate some of problems posed by these challenges. Addressing these challenges will ultimately accelerate the translation of AI research into practical and useful solutions for combating pandemics. 5.4% topic match

5.3%

0.1

2012

[473] Genetic Algorithm for feature selection : application to prediction of mortality during hypotensive episodes in patients with sepsis and severe sepsis Louis Mayaud , L. Tarassenko and G. Clifford Journal Not Provided 2012 - 1 citations - Show abstract - Cite 5.3% topic match

5.3%

1.9

2018

[474] The 2018 World Health Organization SAVE LIVES: Clean Your Hands Campaign targets sepsis in health care H. Saito, ..., and D. Pittet Intensive Care Medicine 2018 - 12 citations - Show abstract - Cite 5.3% topic match

5.2%

1.0

2021

[475] Towards real-time diagnosis for pediatric sepsis using graph neural network and ensemble methods. X. Chen, ..., and X. Tang European review for medical and pharmacological sciences 2021 - 3 citations - Show abstract - Cite Abstract: OBJECTIVE The rapid onset of pediatric sepsis and the short optimal time for resuscitation pose a severe threat to children's health in the ICU. Timely diagnosis and intervention are essential to curing sepsis, but there is a lack of research on the prediction of sepsis at shorter time intervals. This study proposes a predictive model towards real-time diagnosis of sepsis to help reduce the time to first antibiotic treatment. PATIENTS AND METHODS The dataset used in this paper was obtained from the pediatric intensive care unit of Shanghai Children's Medical Center and consisted of the initial examination records of patients admitted to the hospital. The data included six groups of laboratory tests: medical history, physical examination, blood gas analysis, routine blood tests, serological tests, and coagulation tests. We divided the admission examination into three stages and proposed a sepsis prediction model towards real-time diagnosis based on local information to shorten waiting time for treatment. The model extracts homogeneous features from patient groups in real-time using a graph neural network and uses the deep forest to learn from homogeneous features and laboratory data to give a comprehensive prediction at the current stage. Discriminative features of each stage are used as augmented information for the next phase, finally achieving self-optimization of global judgment, assisting in pre-allocation of medical resources and providing timely medical assistance to sepsis patients. RESULTS Based on the first stage, second stage, and full test, the AUCs of our model were 93.63%, 96.73%, and 97.58%, respectively, and the F1-scores were 77.35%, 85.71%, and 86.48%, respectively. The models gave relatively accurate predictions at each stage. CONCLUSIONS The prediction model toward a real-time diagnosis of sepsis shows more accurate predictions at each stage compared to other control methods. When the first two stages of data are obtained as input, the model accuracy is close to using complete test data, which can help compress the time to diagnosis to about an hour after the test and significantly reduce waiting time. 5.2% topic match

5.2%

4.3

2022

[476] Artificial Intelligence in Infection Management in the ICU Thomas De Corte, ..., and J. D. De Waele Critical Care 2022 - 10 citations - Show abstract - Cite 5.2% topic match

5.2%

1.7

2017

[477] Diagnosing sepsis: a step forward, and possibly a step back. S. Simpson Annals of translational medicine 2017 - 12 citations - Show abstract - Cite 5.2% topic match

5.0%

0.5

2022

[478] Evolution of Heart Rate Complexity Indices in the Early Detection of Neonatal Sepsis Maria Ribeiro, ..., and T. Henriques 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) 2022 - 1 citations - Show abstract - Cite 5.0% topic match

5.0%

8.6

2014

[479] Clinical Decision Support for Early Recognition of Sepsis* Robert C. Amland and Kristin Hahn-Cover American Journal of Medical Quality 2014 - 84 citations - Show abstract - Cite 5.0% topic match

4.8%

0.0

2017

[480] Bringing our Toys to your Sandbox: Developing Database-Driven EMR Indifferent Sepsis Alerts Kristen E. Miller, ..., and R. Arnold Proceedings of the International Symposium of Human Factors and Ergonomics in Healthcare 2017 - 0 citations - Show abstract - Cite 4.8% topic match

4.7%

1.1

2022

[481] Artificial intelligence in intensive care: moving towards clinical decision support systems. Jonathan Montomoli, ..., and C. Ince Minerva anestesiologica 2022 - 2 citations - Show abstract - Cite 4.7% topic match

4.7%

None

[482] Journal of Health Economics and Outcomes Research The Potential Cost and Cost-effectiveness Impact of Using a Machine Learning Algorithm for Early Detection of Sepsis in Intensive Care Units in Sweden No author found Journal Not Provided None - 6 citations - Show abstract - Cite Abstract: information. ABSTRACT Background: Early diagnosis of sepsis has been shown to reduce treatment delays, increase appropriate care, and reduce mortality. The sepsis machine learning algorithm NAVOY® Sepsis, based on variables routinely collected at intensive care units (ICUs), has shown excellent predictive properties. However, the economic consequences of forecasting the onset of sepsis are unknown. Objectives: The potential cost and cost-effectiveness impact of a machine learning algorithm forecasting the onset of sepsis was estimated in an ICU setting. Methods: A health economic model has been developed to capture short-term and long-term consequences of sepsis. The model is based on findings from a randomized, prospective clinical evaluation of NAVOY® Sepsis and from literature sources. Modeling the relationship between time from sepsis onset to treatment and prevalence of septic shock and in-hospital mortality was of particular interest. The model base case assumes that the time to treatment coincides with the time to detection and that the algorithm predicts sepsis 3 hours prior to onset. Total costs include the costs of the prediction algorithm, days spent at the ICU and hospital ward, and long-term consequences. Costs are estimated for an average patient admitted to the ICU and for the healthcare system. The reference method is sepsis diagnosis in accordance with clinical practice. Results: In Sweden, the total cost per patient amounts to €16 436 and €16 512 for the algorithm and current practice arms, respectively, implying a potential cost saving per patient of €76. The largest cost saving is for the ICU stay, which is reduced by 0.16 days per patient (5860 ICU days for the healthcare sector) resulting in a cost saving of €1009 per ICU patient. Stochastic scenario analysis showed that NAVOY® Sepsis was a dominant treatment option in most scenarios and well below an established threshold of €20 000 per quality-adjusted life-year. A 3-hour faster detection implies a reduction in in-hospital mortality, resulting in 356 lives saved per year. Conclusions: A sepsis prediction algorithm such as NAVOY® Sepsis reduces the cost per ICU patient and will potentially have a substantial cost-saving and life-saving impact for ICU departments and the healthcare 4.7% topic match

4.6%

0.0

2023

[483] Impact of Advances in Artificial Intelligence on Health Tech Industry Sesha Bhargavi Velagaleti, ..., and D. Vandana International Journal for Research in Applied Science and Engineering Technology 2023 - 0 citations - Show abstract - Cite 4.6% topic match

4.6%

0.0

2023

[484] Impact of Analytics Applying Artificial Intelligence and Machine Learning on Enhancing Intensive Care Unit: A Narrative Review G. Charan, ..., and G. Narang Galician Medical Journal 2023 - 0 citations - Show abstract - Cite 4.6% topic match

4.6%

2.0

2015

[485] Development of a mortality prediction formula due to sepsis/severe sepsis in a medical intensive care unit A. Mohan, ..., and N. Wig Lung India : Official Organ of Indian Chest Society 2015 - 18 citations - Show abstract - Cite Abstract: Background: Although sepsis is one of the leading causes of mortality in hospitalized patients, information regarding early predictive factors for mortality and morbidity is limited. Materials and Methods: Patients fulfilling the Infectious Disease Society of America criteria of sepsis within the medical intensive care unit (ICU) were included over two years. Apart from baseline hematological, biochemical, and metabolic parameters, Acute Physiology and Chronic Health Evaluation II (APACHE II), Simplified Acute Physiology Score II and III (SAPS II and SAPS III), and Sequential Organ Function Assessment (SOFA) scores were calculated on day 1 of admission. Patients were followed till death or discharge from the ICU. Results: One hundred patients were enrolled over two years (54% males). The overall mortality was 53%, (69.5% in females, 38.8% in males (P < 0.01). Mortality was 65.7%, 55.7%, and 33.3% in patients with septic shock, severe sepsis, and sepsis, respectively. Patients who died were significantly older than the survivors (mean age, 57.37 ± 20.42 years and 44.29 ± 15.53 years respectively, P < 0.01). Nonsurvivors were significantly more anemic and had higher APACHE II, SAPS II, SAPS III, and SOFA scores. The presence of acute respiratory distress syndrome and renal dysfunction were associated with higher mortality (75% and 70.2%, respectively). There was no significant difference in the duration of mechanical ventilation or ICU stay between survivors and nonsurvivors. On multivariate analysis, significant predictors of mortality with odds ratio greater than 2 included the presence of anemia, SAPS II score greater than 35, SAPS III score greater than 47, and SOFA score greater than 6 at day 1 of admission. Conclusion: Several demographic and laboratory parameters as well as composite critical illness scoring systems are reliable early predictors of mortality in sepsis. A sepsis mortality prediction formula (AIIMS Sepsis Score) based on SAPS II, SAPS III, and SOFA scores and hemoglobin has greater predictive power than these scoring methods individually. Routine use of critical illness scoring systems and a composite mortality prediction formula may provide useful early prognostic information in sepsis/severe sepsis. 4.6% topic match

4.6%

0.0

2012

[486] Acute Phase Proteins – Regulation and Functions of Acute Phase Proteins 212 2 . Obesity in critical disease H. Dückers, ..., and A. Koch Journal Not Provided 2012 - 0 citations - Show abstract - Cite Abstract: Among the different conditions of critical illness leading to admission to an Intensive Care Unit (ICU), sepsis remains the leading cause of death at the non-coronary medical ICU [1]. Even with optimal therapy, mortality rates of severe sepsis and septic shock are about 40 to 50% [2, 3]. Although there are numerous studies with varying methods from different countries, the incidence of severe sepsis is constantly approximately one out of ten admissions to all ICUs worldwide [4]. With millions of individuals concerned every year, worldwide sepsis is one of the major healthcare problems today. The proportion of severe sepsis, and case fatal outcomes increased during the last years [2]. It is crucial to establish the diagnosis sepsis as early as possible and to identify its origin, in order to initiate an appropriate therapy permitting to achieve the best possible outcome [5]. Sepsis is defined as a systemic inflammatory response syndrome (SIRS) caused by an infection. The association with organ dysfunction or sepsis-induced hypotension is termed severe sepsis. Septic shock, as a subset of severe sepsis, is characterized by sepsis-induced hypotension, persisting despite adequate fluid resuscitation [6]. Early differentiation between sepsis and SIRS is a considerable problem in the treatment of patients on ICU. Due to the early systemic release of inflammatory cytokines as compared with synthesis of acutephase-proteins, cytokines have been widely investigated for their diagnostic potential in predicting sepsis [7]. Nevertheless, until now the perfect biomarker for differentiation of sepsis and SIRS has not been found yet and ongoing research focuses on identification of appropriate diagnostic biomarkers for sepsis [8]. Despite a growing number of studies, the physiopathology of sepsis is not satisfyingly understood. Data show that physiopathology is characterized by a large number of proand anti-inflammatory cytokines and mediators of inflammation with complex interactions [9]. For instance, the application of a single bolus i.v. infusion of endotoxin to a healthy individual leads to the expression of 3147 genes, (> 10% of the human genome) [10]. These mediators and cytokines lead to endothelial dysfunction and activation of inflammatory and coagulation pathways as reaction to the invasion of a pathogen [11]. In order to reduce the sepsis-related high mortality, a better understanding of common pathogenic mechanisms of sepsis and other critical diseases is needed, potentially resulting in more effective treatment options. 4.6% topic match

4.5%

42.4

2019

[487] Artificial Intelligence and Surgical Decision-Making. T. Loftus, ..., and A. Bihorac JAMA surgery 2019 - 196 citations - Show abstract - Cite 4.5% topic match

4.4%

0.5

2022

[488] Risk factors for the prognosis of patients with sepsis in intensive care units Xiaowei Gai, ..., and Qiuyan Wang PLoS ONE 2022 - 1 citations - Show abstract - Cite 4.4% topic match

4.4%

13.6

2009

[489] Continuous Multi-Parameter Heart Rate Variability Analysis Heralds Onset of Sepsis in Adults Saif Ahmad, ..., and A. Seely PLoS ONE 2009 - 203 citations - Show abstract - Cite Abstract: Background Early diagnosis of sepsis enables timely resuscitation and antibiotics and prevents subsequent morbidity and mortality. Clinical approaches relying on point-in-time analysis of vital signs or lab values are often insensitive, non-specific and late diagnostic markers of sepsis. Exploring otherwise hidden information within intervals-in-time, heart rate variability (HRV) has been documented to be both altered in the presence of sepsis, and correlated with its severity. We hypothesized that by continuously tracking individual patient HRV over time in patients as they develop sepsis, we would demonstrate reduced HRV in association with the onset of sepsis. Methodology/Principal Findings We monitored heart rate continuously in adult bone marrow transplant (BMT) patients (n = 21) beginning a day before their BMT and continuing until recovery or withdrawal (12±4 days). We characterized HRV continuously over time with a panel of time, frequency, complexity, and scale-invariant domain techniques. We defined baseline HRV as mean variability for the first 24 h of monitoring and studied individual and population average percentage change (from baseline) over time in diverse HRV metrics, in comparison with the time of clinical diagnosis and treatment of sepsis (defined as systemic inflammatory response syndrome along with clinically suspected infection requiring treatment). Of the 21 patients enrolled, 4 patients withdrew, leaving 17 patients who completed the study. Fourteen patients developed sepsis requiring antibiotic therapy, whereas 3 did not. On average, for 12 out of 14 infected patients, a significant (25%) reduction prior to the clinical diagnosis and treatment of sepsis was observed in standard deviation, root mean square successive difference, sample and multiscale entropy, fast Fourier transform, detrended fluctuation analysis, and wavelet variability metrics. For infected patients (n = 14), wavelet HRV demonstrated a 25% drop from baseline 35 h prior to sepsis on average. For 3 out of 3 non-infected patients, all measures, except root mean square successive difference and entropy, showed no significant reduction. Significant correlation was present amongst these HRV metrics for the entire population. Conclusions/Significance Continuous HRV monitoring is feasible in ambulatory patients, demonstrates significant HRV alteration in individual patients in association with, and prior to clinical diagnosis and treatment of sepsis, and merits further investigation as a means of providing early warning of sepsis. 4.4% topic match

4.3%

0.0

2023

[490] Alert to Action: Implementing Artificial Intelligence–Driven Clinical Decision Support Tools for Sepsis A. Fixler, ..., and Jason Hill The Ochsner Journal 2023 - 0 citations - Show abstract - Cite 4.3% topic match

4.2%

8.4

2016

[491] Evaluating the impact of a computerized surveillance algorithm and decision support system on sepsis mortality S. Manaktala and Stephen Claypool Journal of the American Medical Informatics Association : JAMIA 2016 - 69 citations - Show abstract - Cite 4.2% topic match

4.2%

0.0

2018

[492] "Flying blind" or "in plain sight"? V. Sandfort Journal of emergency and critical care medicine 2018 - 0 citations - Show abstract - Cite 4.2% topic match

4.1%

0.0

2017

[493] Improving Early Sepsis Identification on Inpatient Units Monica Schurle Journal Not Provided 2017 - 0 citations - Show abstract - Cite Abstract: Sepsis is a serious complication, which is initiated by the body’s extreme response to an infection. If sepsis is not identified and treated promptly, it can rapidly lead to tissue damage, organ failure and death. In order to reduce the number of patients who decline to sepsis in hospital, an efficient sepsis protocol needs to be implemented. Nursing practices, knowledge, and early recognition of systemic inflammatory response syndrome (SIRS) were assessed and measured in order to implement effective interventions. A root cause analysis was conducted to identify any discrepancies with compliance performing the sepsis screening in a timely manner, identify contributing factors in sepsis treatment delays, and ensure that the sepsis process map is reflective of the hospital policy. The Clinical Nurse Leader students under the direction of the Sepsis Committee Director developed a Sepsis Screening Observation Checklist to observe the nurses on the unit to determine if in fact the sepsis screening was completed. A chart review audit was conducted by using a Sepsis Chart Screening Data form, which allowed students to review EMR charts of 100 patients in five different nursing units. The students also provided nurses with questionnaires to assess their knowledge on sepsis and about their sepsis hospital policy and protocol. Results demonstrated that vital signs are reported to nurses in a timely manner 50% of the time, the greatest contributor to delays in the treatment of sepsis are labs, and only 38% of nurses feel adequate educational resources regarding sepsis are provided to nurses. A nurse’s understanding and knowledge of sepsis is vital in identifying septic patterns and the necessary interventions a nurse needs to take in order to keep his/her patient safe. IMPROVING EARLY SEPSIS IDENTIFICATION 3 Improving Early Sepsis Identification on Inpatient Units Sepsis is a life-threatening medical emergency that requires prompt interventions to reduce adverse complications such as organ failure and death. According to the Centers for Disease Control and Prevention (CDC), more than 1.5 million people in the United States suffer from sepsis each year, about one in every three patients who die in the hospital setting have sepsis, and at least 250,000 Americans die each year as a result of sepsis ("Data Reports | Sepsis | CDC," 2017). Due to the high mortality and morbidity rates, sepsis has become an area of focus within the hospital setting to identify early and implement evidence-based practices to promote recognition and uniform policies for treatment. Sepsis affects approximately 750,000 people in the United States, with mortality rates of 28% to 50% and costing $17 billion each year (Winterbottom, Seoane, Sundell, Niazi & Nash, 2011). Routine sepsis screening is one essential method utilized to identify systemic inflammatory response syndrome (SIRS) early so that prompt interventions are initiated to prevent adverse outcomes, optimize patient outcomes and reduce cost expenditure. Literature review was conducted utilizing CINAHL Complete and PubMed databases. In the CINAHL Complete database, utilizing phrases such as “early sepsis identification” which gave 54 articles retrieved literature review. Also, additional phrases “sepsis checklist” generated 4 articles and “improving sepsis screening” and “inpatient units” had 788 articles total. The PubMed database showed 388 articles using “early recognition of sepsis.” The nursing knowledge and understanding of sepsis identification and treatment, as well as the nursing culture as a whole, will help identify areas where IMPROVING EARLY SEPSIS IDENTIFICATION 4 improvements can be developed to improve patient outcomes. By conducting a retrospective medical record review, the efficacy of the current sepsis protocol will also be evaluated. Ensuring that the hospital has a well-developed sepsis protocol, which aligns with the international guidelines for the management of sepsis and septic shock released by The Surviving Sepsis Campaign (SSC), as well as the guidelines set by the Centers for Medicare and Medicaid Services (CMS), will help facilitate the early identification and appropriate treatment of sepsis. Methods Microsystem Assessment This large, metropolitan healthcare facility is a 384-bed hospital facility that provides an array of medical services including the following: Level II Trauma Center, emergency, oncology, cardiovascular, pediatrics, behavioral health, skilled nursing and obstetrics. The interdisciplinary team is responsible for monitoring these patients and improving their well being by providing excellent care with social justice and dignity (x). The vision of this institution states, “our vision is to be a values-driven integrated health care delivery system in collaboration with those who share our values” (x). This institution strives on promoting quality, patient-centered care through advocacy and preserving the health of the community. The values of the hospital include respect, caring, integrity, passion and stewardship. It is also a non-profit organization and is heavily dependent on grants, charitable donations and endowments to continue providing medical services within this area. This hospital “was incorporated in 1983 as a nonprofit public benefit corporation and is governed by a volunteer Board of Trustees” (x). IMPROVING EARLY SEPSIS IDENTIFICATION 5 The microsystem observed for the sepsis project comprised of five-inpatient units2E, 4, 5, 6 and 8 floors. The emphasis of this project was predominantly focused on the telemetry/medical-surgical floor located on the sixth-floor where the sepsis screening observations were conducted. Also, the purpose of this microsystem is to serve and treat cardiac diseases, especially stroke patients as well oncology, telemetry and medicalsurgical patients. Many of the patients that the hospital serves are uninsured, and they rely on Medi-Cal coverage to receive treatments and services. Approximately, “60% of the Hospital’s inpatient payer mix consisted of Medi-Cal Managed Care (31%) and MediCal Traditional (29%) patients” (x). There is a multi-disciplinary team that oversees the care of each patient which include: physicians, nurse practitioners, registered nurses, respiratory therapists, certified nursing assistants and licensed vocational nurses. Each of these healthcare professionals is a vital asset for to promote patient safety, optimize patient outcomes, and implement quality patient care. The patient care delivery model for the unit is the patient-family centered care model. This model not only focuses on the patient but also incorporates the patient’s family members to be proactive in delivering quality care. Family members play a crucial role in improving patient outcomes by incorporating social, emotional and spiritual wellbeing. In addition, this also improves communication with the patient, family members and the interdisciplinary healthcare team to provide coordinated and effective care. This model encompasses safety, quality, service, and the hospital’s values. Root Cause Analysis A root cause analysis was performed to identify compliance and potential disparities to completing the sepsis-screening checklist for each patient at the beginning IMPROVING EARLY SEPSIS IDENTIFICATION 6 of each shift. A systematic review of the inpatient units’ sepsis protocol maps, policy, algorithm, and screening tool were utilized to identify disparities within the protocols and improve the sepsis protocol and screening. The data was collected through observation audits on the sixth floor noting if the registered nurse completed the sepsis screening between 7:00am and 10:00am, chart review audits, and surveying the registered nurses about the sepsis protocol and obtain a measureable baseline of their knowledge. The Clinical Nurse Leader students along with the collaboration and direction of the Director of the Sepsis Committee performed weekly observational audits. Observational visits were coordinated with the Director of the Sepsis Committee to schedule a time and date to visit the unit and conduct the observations. Generally, the observations were divided into two days with half of the students attending one of the days and then meeting with him for a post-conference to discuss our findings and identify the next objective. The total number of patients audited during this time was 66 patients (See Appendix A for Sepsis Observational Checklist). If time permitted and access to additional units were granted, the Clinical Nurse Leader students would have benefited more if the observational audits were performed during the nurses’ full 12-hour shift, rather than the limited 3-hour morning shift time frame. Also, if the students also had the opportunity to observe if the sepsis screening was done during the night shift would have crucial data to evaluate compliance and identify barriers and not limited to only one specific timeframe. By shadowing the nurses during their entire shift or up until the screening was completed in the EMR, we would have a more precise data of which vital signs were used and when the screening was completed. Furthermore, to maintain the IMPROVING EARLY SEPSIS IDENTIFICATION 7 validity and precision of the audits, the students refrained from disclosing to the nurses the purpose of the audits to remove limitations and skewed data. In addition, a “Sepsis Chart Screening Data” form was utilized to review EMR charts of 100 patients (199 sepsis screeningsboth morning and night shifts for each patient) from all five inpatient units. The chart review for each patient must be a patient age 18-years or older and day 2 post-admission. Furthermore, the registered nurses baseline knowledge was assessed through a questionnaire given to each nurse on the unit. Questionnaire forms were gathered from 32 nurses from all five inpatient units. There was no need to obtain Institutional Review Board (IRB) approv 4.1% topic match

4.1%

0.9

2022

[494] Early prediction of moderate-to-severe condition of inhalation-induced acute respiratory distress syndrome via interpretable machine learning J. Wu, ..., and F. Xie BMC Pulmonary Medicine 2022 - 2 citations - Show abstract - Cite 4.1% topic match

4.1%

2.8

2021

[495] A Deep Learning-Based Sepsis Estimation Scheme Bilal Yaseen Al‐Mualemi and Lu Lu IEEE Access 2021 - 10 citations - Show abstract - Cite 4.1% topic match

4.0%

2.0

2014

[496] Heterogeneous postsurgical data analytics for predictive modeling of mortality risks in intensive care units Yunchao Chen and Hui Yang 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society 2014 - 21 citations - Show abstract - Cite 4.0% topic match

3.9%

1.0

2020

[497] Potential Prognostic Markers in the Heart Rate Variability Features for Early Diagnosis of Sepsis in the Pediatric Intensive Care Unit using Convolutional Neural Network Classifiers P. Amiri, ..., and M. Mirzaaghayan 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) 2020 - 4 citations - Show abstract - Cite 3.9% topic match

3.7%

1.3

2022

[498] Entering the new digital era of intensive care medicine: an overview of interdisciplinary approaches to use artificial intelligence for patients’ benefit O. Old, ..., and J. Kloka European Journal of Anaesthesiology Intensive Care 2022 - 2 citations - Show abstract - Cite 3.7% topic match

3.7%

0.0

2019

[499] Simulating Uncertainty of Early Warning Scores in Sepsis Detection A. Jazayeri, ..., and R. Arnold Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics 2019 - 0 citations - Show abstract - Cite 3.7% topic match

3.7%

0.9

2009

[500] Spectral analysis of heart period and pulse transit time derived from electrocardiogram and photoplethysmogram in sepsis patients Collin H. H. Tang, ..., and N. Lovell 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society 2009 - 13 citations - Show abstract - Cite 3.7% topic match

3.6%

0.0

2022

[501] Artificial Intelligence in Gastroenterology D. Juneja, ..., and O. Singh Journal Not Provided 2022 - 0 citations - Show abstract - Cite 3.6% topic match

3.5%

3.2

2022

[502] Development and Trends in Artificial Intelligence in Critical Care Medicine: A Bibliometric Analysis of Related Research over the Period of 2010–2021 Xiao Cui, ..., and Yuxin Leng Journal of Personalized Medicine 2022 - 5 citations - Show abstract - Cite 3.5% topic match

3.4%

3.2

2022

[503] Artificial intelligence and clinical deterioration James Malycha, ..., and O. Redfern Current Opinion in Critical Care 2022 - 7 citations - Show abstract - Cite 3.4% topic match

3.3%

0.5

2022

[504] Artificial Intelligence in e-Health: A Review of Current Status in Healthcare and Future Possible Scope of Research Sapna Katiyar and Artika Farhana Journal of Computer Science 2022 - 1 citations - Show abstract - Cite 3.3% topic match

3.3%

0.0

2021

[505] Predictive Models of Intensive Care Unit Mortality - Severity of Illness Scores or Artificial Intelligence instruments? - Literature Review and Metanalysis (Preprint) Cristina Barboi, ..., and L. Muhammad https://doi.org/10.2196/preprints.35293 2021 - 0 citations - Show abstract - Cite Abstract: BACKGROUND The Severity of Illness Scores (SIS)- Acute Physiology and Chronic Health Evaluation (APACHE), Simplified Acute Physiology Score (SAPS), and Sequential Organ Failure Assessment (SOFA) - are current risk stratification and mortality prediction tools used in Intensive Care Units (ICU) across the globe, and rely on scores that assess disease severity on admission. Developers of Artificial Intelligence (AI) or Machine Learning (ML) models predictive of ICU mortality use the SIS performance as a reference point when reporting the performance of these computational constructs. OBJECTIVE Using systematic review and meta-analysis, we evaluated studies that compare ML-based mortality prediction models to SIS-based models. The review should inform clinicians regarding the prognostic value of ML-based ICU mortality prediction models compared with SIS models and their validity in supporting clinical decision-making. METHODS We performed a systematic search using PubMed, Scopus, Embase, and IEEE databases. Studies that report the performance of newly developed ML models predictive of ICU mortality and compare it with the performance of SIS models on the same datasets were eligible for inclusion. ML and the SIS models with a reported Area Under the Receiver Operating Characteristic (AUROC) curve were included in the meta-analysis to identify the group with superior performance. Data were extracted with guidance from the CHARMS (Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies) checklist[1] and was appraised for risk of bias and applicability using PROBAST (A Tool to Assess the Risk of Bias and Applicability of Prediction Model Studies ) [2]. RESULTS After screening the literature, we identified and included 20 papers containing 47 ML models based on seven types of algorithms that were compared with three types of SIS models. The AUROC for predicting ICU mortality ranged between 0.828-0.875 for ML-based models and between 0.707-0.760 for SI-based models. We noted substantial heterogeneity among the models reported, and considerable variation among the AUROC estimates for both ML and SIS model types. Due to the high degree of heterogeneity, we performed a limited random-effect meta-analysis of externally validated subgroups of ML models and the subgroups of SIS used for comparison. CONCLUSIONS ML-based models can accurately predict ICU mortality as an alternative to traditional scoring models. The high degree of heterogeneity observed within and between studies limit the assessment of pooled results. The differences in development strategies, validation, statistical, and computational methods that these models rely on impede a head-to-head comparison, and we cannot declare the superiority of one model over the other. Consequently, we make no recommendation regarding the ML-based ICU mortality prediction models’ performance in clinical practice. To bridge the knowledge gap from design to practice, ML model developers must provide explainer models and make those knowledge objects reproducible, interoperable, and transparent[3]. CLINICALTRIAL the review was registered and approved by the international prospective register of systematic reviews, PROSPERO (reference number CRD42021203871). 3.3% topic match

3.3%

12.1

2020

[506] Machine learning for early detection of sepsis: an internal and temporal validation study A. Bedoya, ..., and Cara O'Brien JAMIA Open 2020 - 52 citations - Show abstract - Cite Abstract: Abstract Objective Determine if deep learning detects sepsis earlier and more accurately than other models. To evaluate model performance using implementation-oriented metrics that simulate clinical practice. Materials and Methods We trained internally and temporally validated a deep learning model (multi-output Gaussian process and recurrent neural network [MGP–RNN]) to detect sepsis using encounters from adult hospitalized patients at a large tertiary academic center. Sepsis was defined as the presence of 2 or more systemic inflammatory response syndrome (SIRS) criteria, a blood culture order, and at least one element of end-organ failure. The training dataset included demographics, comorbidities, vital signs, medication administrations, and labs from October 1, 2014 to December 1, 2015, while the temporal validation dataset was from March 1, 2018 to August 31, 2018. Comparisons were made to 3 machine learning methods, random forest (RF), Cox regression (CR), and penalized logistic regression (PLR), and 3 clinical scores used to detect sepsis, SIRS, quick Sequential Organ Failure Assessment (qSOFA), and National Early Warning Score (NEWS). Traditional discrimination statistics such as the C-statistic as well as metrics aligned with operational implementation were assessed. Results The training set and internal validation included 42 979 encounters, while the temporal validation set included 39 786 encounters. The C-statistic for predicting sepsis within 4 h of onset was 0.88 for the MGP–RNN compared to 0.836 for RF, 0.849 for CR, 0.822 for PLR, 0.756 for SIRS, 0.619 for NEWS, and 0.481 for qSOFA. MGP–RNN detected sepsis a median of 5 h in advance. Temporal validation assessment continued to show the MGP–RNN outperform all 7 clinical risk score and machine learning comparisons. Conclusions We developed and validated a novel deep learning model to detect sepsis. Using our data elements and feature set, our modeling approach outperformed other machine learning methods and clinical scores. 3.3% topic match

3.3%

0.0

2017

[507] 9 Adipocytokines in Severe Sepsis and Septic Shock H. Dückers, ..., and A. Koch Journal Not Provided 2017 - 0 citations - Show abstract - Cite Abstract: Among the different conditions of critical illness leading to admission to an Intensive Care Unit (ICU), sepsis remains the leading cause of death at the non-coronary medical ICU [1]. Even with optimal therapy, mortality rates of severe sepsis and septic shock are about 40 to 50% [2, 3]. Although there are numerous studies with varying methods from different countries, the incidence of severe sepsis is constantly approximately one out of ten admissions to all ICUs worldwide [4]. With millions of individuals concerned every year, worldwide sepsis is one of the major healthcare problems today. The proportion of severe sepsis, and case fatal outcomes increased during the last years [2]. It is crucial to establish the diagnosis sepsis as early as possible and to identify its origin, in order to initiate an appropriate therapy permitting to achieve the best possible outcome [5]. Sepsis is defined as a systemic inflammatory response syndrome (SIRS) caused by an infection. The association with organ dysfunction or sepsis-induced hypotension is termed severe sepsis. Septic shock, as a subset of severe sepsis, is characterized by sepsis-induced hypotension, persisting despite adequate fluid resuscitation [6]. Early differentiation between sepsis and SIRS is a considerable problem in the treatment of patients on ICU. Due to the early systemic release of inflammatory cytokines as compared with synthesis of acutephase-proteins, cytokines have been widely investigated for their diagnostic potential in predicting sepsis [7]. Nevertheless, until now the perfect biomarker for differentiation of sepsis and SIRS has not been found yet and ongoing research focuses on identification of appropriate diagnostic biomarkers for sepsis [8]. Despite a growing number of studies, the physiopathology of sepsis is not satisfyingly understood. Data show that physiopathology is characterized by a large number of proand anti-inflammatory cytokines and mediators of inflammation with complex interactions [9]. For instance, the application of a single bolus i.v. infusion of endotoxin to a healthy individual leads to the expression of 3147 genes, (> 10% of the human genome) [10]. These mediators and cytokines lead to endothelial dysfunction and activation of inflammatory and coagulation pathways as reaction to the invasion of a pathogen [11]. In order to reduce the sepsis-related high mortality, a better understanding of common pathogenic mechanisms of sepsis and other critical diseases is needed, potentially resulting in more effective treatment options. 3.3% topic match

3.2%

18.6

2023

[508] An integrative review on the acceptance of artificial intelligence among healthcare professionals in hospitals S. Lambert, ..., and A. Stephan NPJ Digital Medicine 2023 - 21 citations - Show abstract - Cite 3.2% topic match

3.1%

0.0

2023

[509] A review on the advancements and challenges of artificial intelligence based models for predictive maintenance of water injection pumps in the oil and gas industry Salama Almazrouei, ..., and Abdalla Alnaqbi SN Applied Sciences 2023 - 0 citations - Show abstract - Cite 3.1% topic match

3.1%

4.0

2018

[510] Current monitoring and innovative predictive modeling to improve care in the pediatric cardiac intensive care unit. Mary K. Olive and G. Owens Translational pediatrics 2018 - 25 citations - Show abstract - Cite 3.1% topic match

3.0%

7.5

2020

[511] Development and Prospective Validation of a Deep Learning Algorithm for Predicting Need for Mechanical Ventilation PhD Supreeth P. Shashikumar, ..., and M. B. Westover Chest 2020 - 27 citations - Show abstract - Cite 3.0% topic match

3.0%

0.0

2023

[512] LoRaWAN-Based Artificial Intelligence Intensive Care Unit Framework for Tracking Patients With Severe Pneumonia A. K M and S. Baskar IEEE Sensors Letters 2023 - 0 citations - Show abstract - Cite 3.0% topic match

2.9%

0.0

2023

[513] Role of Artificial Intelligence in CXR Interpretation in Pediatric Intensive Care Unit Ain Shams University Maha Mahmoud, ..., and George Ezzat Elkess Yacoub QJM: An International Journal of Medicine 2023 - 0 citations - Show abstract - Cite 2.9% topic match

2.9%

0.1

2015

[514] The benefits of measuring heart rate variability in sepsis P. Pladys, ..., and A. Beuchée Journal Not Provided 2015 - 1 citations - Show abstract - Cite 2.9% topic match

2.8%

5.1

2019

[515] Machine-Learning-Based Laboratory Developed Test for the Diagnosis of Sepsis in High-Risk Patients J. Calvert, ..., and R. Das Diagnostics 2019 - 28 citations - Show abstract - Cite 2.8% topic match

2.8%

0.4

2016

[516] What to Do When Haloperidol Fails to Treat Agitated Delirium: Is Dexmedetomidine the Next Step? Beth M. T. Teegarden and D. Prough Critical care medicine 2016 - 3 citations - Show abstract - Cite 2.8% topic match

2.8%

0.6

2023

[517] Invasive mechanical ventilation probability estimation using machine learning methods based on non-invasive parameters Huiquan Wang, ..., and Guang-fang Zhang Biomed. Signal Process. Control. 2023 - 1 citations - Show abstract - Cite 2.8% topic match

2.7%

6.4

2023

[518] Artificial Intelligence in Healthcare: A Bibliometric Analysis Bahiru Legesse Jimma Telematics and Informatics Reports 2023 - 10 citations - Show abstract - Cite 2.7% topic match

2.7%

6.3

2021

[519] Artificial Intelligence for Hospital Health Care: Application Cases and Answers to Challenges in European Hospitals M. Klumpp, ..., and R. Delgado-Gonzalo Healthcare 2021 - 19 citations - Show abstract - Cite 2.7% topic match

2.7%

1.6

2021

[520] Current Progress on Biosensors and Point-of-Care Devices for Sepsis Diagnosis Dimitra Tsounidi, ..., and I. Raptis IEEE Sensors Journal 2021 - 5 citations - Show abstract - Cite 2.7% topic match

2.7%

0.0

2020

[521] Authors reply to Pinninti et al., Niyogi and Baheti A. Mahajan, ..., and S. Rane Cancer Research, Statistics, and Treatment 2020 - 0 citations - Show abstract - Cite 2.7% topic match

2.6%

8.1

2020

[522] Validation of automated sepsis surveillance based on the Sepsis-3 clinical criteria against physician record review in a general hospital population: observational study using electronic health records data J. Valik, ..., and P. Nauclér BMJ Quality & Safety 2020 - 36 citations - Show abstract - Cite Abstract: Background Surveillance of sepsis incidence is important for directing resources and evaluating quality-of-care interventions. The aim was to develop and validate a fully-automated Sepsis-3 based surveillance system in non-intensive care wards using electronic health record (EHR) data, and demonstrate utility by determining the burden of hospital-onset sepsis and variations between wards. Methods A rule-based algorithm was developed using EHR data from a cohort of all adult patients admitted at an academic centre between July 2012 and December 2013. Time in intensive care units was censored. To validate algorithm performance, a stratified random sample of 1000 hospital admissions (674 with and 326 without suspected infection) was classified according to the Sepsis-3 clinical criteria (suspected infection defined as having any culture taken and at least two doses of antimicrobials administered, and an increase in Sequential Organ Failure Assessment (SOFA) score by >2 points) and the likelihood of infection by physician medical record review. Results In total 82 653 hospital admissions were included. The Sepsis-3 clinical criteria determined by physician review were met in 343 of 1000 episodes. Among them, 313 (91%) had possible, probable or definite infection. Based on this reference, the algorithm achieved sensitivity 0.887 (95% CI: 0.799 to 0.964), specificity 0.985 (95% CI: 0.978 to 0.991), positive predictive value 0.881 (95% CI: 0.833 to 0.926) and negative predictive value 0.986 (95% CI: 0.973 to 0.996). When applied to the total cohort taking into account the sampling proportions of those with and without suspected infection, the algorithm identified 8599 (10.4%) sepsis episodes. The burden of hospital-onset sepsis (>48 hour after admission) and related in-hospital mortality varied between wards. Conclusions A fully-automated Sepsis-3 based surveillance algorithm using EHR data performed well compared with physician medical record review in non-intensive care wards, and exposed variations in hospital-onset sepsis incidence between wards. 2.6% topic match

2.6%

1.0

2020

[523] External validation of the sepsis severity score Marek Wełna, ..., and A. Kübler International Journal of Immunopathology and Pharmacology 2020 - 4 citations - Show abstract - Cite 2.6% topic match

2.6%

6.3

2016

[524] Sepsis-3 definitions predict ICU mortality in a low–middle-income country B. Besen, ..., and Marcelo Park Annals of Intensive Care 2016 - 49 citations - Show abstract - Cite 2.6% topic match

2.5%

0.0

2023

[525] Development of a Determinant Framework to Guide the Translation of AI Systems in Clinical Care A. Owoyemi 2023 IEEE 11th International Conference on Healthcare Informatics (ICHI) 2023 - 0 citations - Show abstract - Cite 2.5% topic match

2.4%

359.9

2016

[526] Experimental And Quasi Experimental Designs For Research Petra Kaufmann Journal Not Provided 2016 - 3084 citations - Show abstract - Cite 2.4% topic match

2.4%

2.6

1978

[527] The psychology of death, dying, and bereavement R. Schulz Journal Not Provided 1978 - 121 citations - Show abstract - Cite 2.4% topic match

2.4%

0.9

2005

[528] Sepsis and organ dysfunction: an ongoing challenge. A. Gullo, ..., and R. Tufano Minerva anestesiologica 2005 - 16 citations - Show abstract - Cite Abstract: In recent years the problem of infection has become increasingly significant, especially in intensive care hospital wards such as Intensive Care Units (ICU), emergency medicine, surgery and critically ill patient care departments. Sepsis is a complex, multifactorial syndrome that can develop into conditions of different severity, described as severe sepsis or septic shock. In these conditions the triggering event may coincide with the functional impairment of one or more vital organs or systems, thus leading to poorer prognosis in patients with overt signs of sepsis or systemic inflammation syndromes. The available data are quite alarming, as most prevention and treatment is performed empirically and requires considerable human and technological resources. Clinical signs are often misleading and, in some circumstances, it may be difficult or even impossible to identify the source of the infection which might otherwise be removed relatively simply, using proper antimicrobial treatment or a less invasive surgical removal of the area from which the infection originates based on needle-guided radiology. In addition, the complex pathophysiological mechanisms involved can be an obstacle to gaining a full understanding of the various biohumoral interactions or mediators action mechanisms. It may not be easy to enroll patients belonging to homogeneous groups in terms of age, underlining disease, immune profile or genetic predisposition, although the use of specific severity indexes has proved helpful also to establish the prognosis. Although the interpretation of generalised inflammation as a warning sign also in the absence of clear signs of infection or a state of overt inflammation has to rely largely on simple intuition, it has helped to drive experimental and clinical research work towards the investigation of interaction between different factors such as infection and sepsis, or inflammation and coagulation. An additional useful tool is the possibility of modulating the endothelial response which may support the process of disseminated thrombosis typical of sepsis evolution. In this context the improvement of standards of care can shed light on the efficacy of different treatments. 2.4% topic match

2.3%

6.4

2018

[529] Current aspects in sepsis approach. Turning things around F. J. Candel, ..., and Pablo Vidal Revista Española de Quimioterapia 2018 - 39 citations - Show abstract - Cite Abstract: ABSTRACT The incidence and prevalence of sepsis depend on the definitions and records that we use and we may be underestimating their impact. Up to 60% of the cases come from the community and in 30-60% we obtain microbiological information. Sometimes its presentation is ambiguous and there may be a delay in its detection, especially in the fragile population. Procalcitonin is the most validated biomarker for bacterial sepsis and the one that best discriminates the non-infectious cause. Presepsin and pro-adrenomedullin are useful for early diagnosis, risk stratification and prognosis in septic patients. The combination of biomarkers is even more useful to clarify an infectious cause than any isolated biomarker. Resuscitation with artificial colloids has worse results than crystalloids, especially in patients with renal insufficiency. The combination of saline solution and balanced crystalloids is associated with a better prognosis. Albumin is only recommended in patients who require a large volume of fluids. The modern molecular methods on the direct sample or the identification by MALDI-TOF on positive blood culture have helped to shorten the response times in diagnosis, to optimize the antibiotic treatment and to facilitate stewardship programs. The hemodynamic response in neonates and children is different from that in adults. In neonatal sepsis, persistent pulmonary hypertension leads to an increase in right ventricular afterload and heart failure with hepatomegaly. Hypotension, poor cardiac output with elevated systemic vascular resistance (cold shock) is often a terminal sign in septic shock. Developing ultra-fast Point-of-Care tests (less than 30 minutes), implementing technologies based on omics, big data or massive sequencing or restoring “healthy” microbiomes in critical patients after treatment are the main focuses of research in sepsis. The main benefits of establishing a sepsis code are to decrease the time to achieve diagnosis and treatment, improve organization, unify criteria, promote teamwork to achieve common goals, increase participation, motivation and satisfaction among team members, and reduce costs. 2.3% topic match

2.3%

0.5

2009

[530] Time-frequency relationships between heart rate and respiration: A diagnosis tool for late onset sepsis in sick premature infants G. Carrault, ..., and A. Hernández 2009 36th Annual Computers in Cardiology Conference (CinC) 2009 - 7 citations - Show abstract - Cite 2.3% topic match

2.3%

0.9

2020

[531] A STUDY DEPICTING THE ADVENT OF ARTIFICIAL INTELLIGENCE IN HEALTH CARE J.Paruvathavardhini, ..., and S.Brindha Journal Not Provided 2020 - 4 citations - Show abstract - Cite 2.3% topic match

2.3%

0.0

2021

[532] Sepsis prediction via the clinical data integration system in the ICU Qiyu Chen, ..., and Affiliations medRxiv 2021 - 0 citations - Show abstract - Cite 2.3% topic match

2.1%

0.9

1997

[533] Predicting survival in the intensive care unit. John P. Hunt and A. Meyer Current problems in surgery 1997 - 25 citations - Show abstract - Cite 2.1% topic match

2.1%

0.1

2011

[534] Adipocytokines in Severe Sepsis and Septic Shock H. Dückers, ..., and A. Koch https://doi.org/10.5772/23683 2011 - 1 citations - Show abstract - Cite Abstract: Among the different conditions of critical illness leading to admission to an Intensive Care Unit (ICU), sepsis remains the leading cause of death at the non-coronary medical ICU [1]. Even with optimal therapy, mortality rates of severe sepsis and septic shock are about 40 to 50% [2, 3]. Although there are numerous studies with varying methods from different countries, the incidence of severe sepsis is constantly approximately one out of ten admissions to all ICUs worldwide [4]. With millions of individuals concerned every year, worldwide sepsis is one of the major healthcare problems today. The proportion of severe sepsis, and case fatal outcomes increased during the last years [2]. It is crucial to establish the diagnosis sepsis as early as possible and to identify its origin, in order to initiate an appropriate therapy permitting to achieve the best possible outcome [5]. Sepsis is defined as a systemic inflammatory response syndrome (SIRS) caused by an infection. The association with organ dysfunction or sepsis-induced hypotension is termed severe sepsis. Septic shock, as a subset of severe sepsis, is characterized by sepsis-induced hypotension, persisting despite adequate fluid resuscitation [6]. Early differentiation between sepsis and SIRS is a considerable problem in the treatment of patients on ICU. Due to the early systemic release of inflammatory cytokines as compared with synthesis of acutephase-proteins, cytokines have been widely investigated for their diagnostic potential in predicting sepsis [7]. Nevertheless, until now the perfect biomarker for differentiation of sepsis and SIRS has not been found yet and ongoing research focuses on identification of appropriate diagnostic biomarkers for sepsis [8]. Despite a growing number of studies, the physiopathology of sepsis is not satisfyingly understood. Data show that physiopathology is characterized by a large number of proand anti-inflammatory cytokines and mediators of inflammation with complex interactions [9]. For instance, the application of a single bolus i.v. infusion of endotoxin to a healthy individual leads to the expression of 3147 genes, (> 10% of the human genome) [10]. These mediators and cytokines lead to endothelial dysfunction and activation of inflammatory and coagulation pathways as reaction to the invasion of a pathogen [11]. In order to reduce the sepsis-related high mortality, a better understanding of common pathogenic mechanisms of sepsis and other critical diseases is needed, potentially resulting in more effective treatment options. 2.1% topic match

2.1%

1.4

2018

[535] Utility of electronic AKI alerts in intensive care: A national multicentre cohort study J. Holmes, ..., and A. Phillips Journal of Critical Care 2018 - 9 citations - Show abstract - Cite 2.1% topic match

2.1%

0.8

2023

[536] Detailed review on Integrated Healthcare Prediction System Using Artificial Intelligence and Machine Learning D. Parasar, ..., and Kumud Pant 2023 3rd International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE) 2023 - 1 citations - Show abstract - Cite Abstract: The intricacy and expansion of statistics in increased care sector will lead to an increase in the application of artificial intelligence (AI). There are several different AI techniques in use today by consumers, health professionals, and sciences companies. Guidelines for care and prognosis, patient and commitment, and organizational chores are the key application areas. Challenges will prevent the work of health professionals from being substantially computerized for a considerable length of time, despite the fact that AI can do healthcare tasks in many instances equally as well or better than people. Ethics issues and the implementation of artificial intelligence in healthcare are also discussed. AI technology is essential for producing effective healthcare applications. The definition of several effective software programmers may help in the growth of the health predictive model. Computer vision and cloud services are critical elements for building smart healthcare solutions.The collection and analysis of a wide range of health care data may provide useful insights quickly. Artificial intelligence is also crucial in the process of illness detection and prognosis. This smart and efficient approach may help with early illness diagnosis. Sensors connected through wireless networks make it possible to track the actions of a whole population. Sensors embedded in the human body may aid in the recognition of emotions and facial expressions by using neural networks. There is a plethora of technological implementations that contribute to a more advanced data processing procedure.The primary focus of this research is to determine how effectively various efficient technology’s function when used in the development of healthcare prediction models. AI uses a wide variety of sensor-based methods to boost healthcare's efficacy. Another area of study has substantial implications for the healthcare system. To help identify problems in biomedical goods, modelling tools may be provided by machine learning. Wireless sensors allow for continuous monitoring of behaviour by collecting real-time data on the surrounding environment. 2.1% topic match

2.0%

0.5

2022

[537] Exploring Stakeholder Requirements to Enable the Research and Development of Artificial Intelligence Algorithms in a Hospital-Based Generic Infrastructure: Protocol for a Multistep Mixed Methods Study Lina Weinert, ..., and O. Heinze JMIR Research Protocols 2022 - 1 citations - Show abstract - Cite Abstract: Background In recent years, research and developments in advancing artificial intelligence (AI) in health care and medicine have increased. High expectations surround the use of AI technologies, such as improvements for diagnosis and increases in the quality of care with reductions in health care costs. The successful development and testing of new AI algorithms require large amounts of high-quality data. Academic hospitals could provide the data needed for AI development, but granting legal, controlled, and regulated access to these data for developers and researchers is difficult. Therefore, the German Federal Ministry of Health supports the Protected Artificial Intelligence Innovation Environment for Patient-Oriented Digital Health Solutions for Developing, Testing, and Evidence-Based Evaluation of Clinical Value (pAItient) project, aiming to install the AI Innovation Environment at the Heidelberg University Hospital in Germany. The AI Innovation Environment was designed as a proof-of-concept extension of the already existing Medical Data Integration Center. It will establish a process to support every step of developing and testing AI-based technologies. Objective The first part of the pAItient project, as presented in this research protocol, aims to explore stakeholders’ requirements for developing AI in partnership with an academic hospital and granting AI experts access to anonymized personal health data. Methods We planned a multistep mixed methods approach. In the first step, researchers and employees from stakeholder organizations were invited to participate in semistructured interviews. In the following step, questionnaires were developed based on the participants’ answers and distributed among the stakeholders’ organizations to quantify qualitative findings and discover important aspects that were not mentioned by the interviewees. The questionnaires will be analyzed descriptively. In addition, patients and physicians were interviewed as well. No survey questionnaires were developed for this second group of participants. The study was approved by the Ethics Committee of the Heidelberg University Hospital (approval number: S-241/2021). Results Data collection concluded in summer 2022. Data analysis is planned to start in fall 2022. We plan to publish the results in winter 2022 to 2023. Conclusions The results of our study will help in shaping the AI Innovation Environment at our academic hospital according to stakeholder requirements. With this approach, in turn, we aim to shape an AI environment that is effective and is deemed acceptable by all parties. International Registered Report Identifier (IRRID) DERR1-10.2196/42208 2.0% topic match

2.0%

0.2

2004

[538] Department of surgery, Emory University School Of Medicine, Atlanta, Georgia. S. Moore and G. Rozycki Archives of surgery 2004 - 4 citations - Show abstract - Cite 2.0% topic match

2.0%

2.4

2021

[539] Advances in artificial intelligence and deep learning systems in ICU-related acute kidney injury T. Ozrazgat-Baslanti, ..., and A. Bihorac Current Opinion in Critical Care 2021 - 7 citations - Show abstract - Cite 2.0% topic match

1.9%

0.4

2007

[540] Butterfly fauna of Melghat region, Maharashtra Mamata R. Chandrakar, ..., and Sangita Chandrakar Zoos' Print Journal 2007 - 7 citations - Show abstract - Cite 1.9% topic match

1.9%

0.4

2011

[541] Clinical aspects of sepsis. M. Holub and J. Závada Contributions to microbiology 2011 - 5 citations - Show abstract - Cite 1.9% topic match

1.9%

3.6

2023

[542] THE POTENTIAL OF AI IN HEALTHCARE Piyush Gupta International Journal of Advanced Research 2023 - 3 citations - Show abstract - Cite 1.9% topic match

1.8%

0.6

2022

[543] Exploring Stakeholder Requirements to Enable Research and Development of Artificial Intelligence Algorithms in a Hospital-Based Generic Infrastructure: Results of a Multistep Mixed Methods Study Lina Weinert, ..., and O. Heinze JMIR Formative Research 2022 - 1 citations - Show abstract - Cite Abstract: Background Legal, controlled, and regulated access to high-quality data from academic hospitals currently poses a barrier to the development and testing of new artificial intelligence (AI) algorithms. To overcome this barrier, the German Federal Ministry of Health supports the “pAItient” (Protected Artificial Intelligence Innovation Environment for Patient Oriented Digital Health Solutions for developing, testing and evidence-based evaluation of clinical value) project, with the goal to establish an AI Innovation Environment at the Heidelberg University Hospital, Germany. It is designed as a proof-of-concept extension to the preexisting Medical Data Integration Center. Objective The first part of the pAItient project aims to explore stakeholders’ requirements for developing AI in partnership with an academic hospital and granting AI experts access to anonymized personal health data. Methods We designed a multistep mixed methods approach. First, researchers and employees from stakeholder organizations were invited to participate in semistructured interviews. In the following step, questionnaires were developed based on the participants’ answers and distributed among the stakeholders’ organizations. In addition, patients and physicians were interviewed. Results The identified requirements covered a wide range and were conflicting sometimes. Relevant patient requirements included adequate provision of necessary information for data use, clear medical objective of the research and development activities, trustworthiness of the organization collecting the patient data, and data should not be reidentifiable. Requirements of AI researchers and developers encompassed contact with clinical users, an acceptable user interface (UI) for shared data platforms, stable connection to the planned infrastructure, relevant use cases, and assistance in dealing with data privacy regulations. In a next step, a requirements model was developed, which depicts the identified requirements in different layers. This developed model will be used to communicate stakeholder requirements within the pAItient project consortium. Conclusions The study led to the identification of necessary requirements for the development, testing, and validation of AI applications within a hospital-based generic infrastructure. A requirements model was developed, which will inform the next steps in the development of an AI innovation environment at our institution. Results from our study replicate previous findings from other contexts and will add to the emerging discussion on the use of routine medical data for the development of AI applications. International Registered Report Identifier (IRRID) RR2-10.2196/42208 1.8% topic match

1.8%

7.5

2011

[544] Cardiovascular oscillations at the bedside: early diagnosis of neonatal sepsis using heart rate characteristics monitoring J. Moorman, ..., and D. Lake Physiological Measurement 2011 - 95 citations - Show abstract - Cite 1.8% topic match

1.8%

27.6

2006

[545] The surviving sepsis campaign. J. Marshall Critical care and resuscitation : journal of the Australasian Academy of Critical Care Medicine 2006 - 495 citations - Show abstract - Cite 1.8% topic match

1.7%

0.4

2014

[546] Time-Domain, Frequency Domain and non-linear measurements in neonates' Heart Rate Variability with clinical sepsis E. Godoy, ..., and J. Saiz Computing in Cardiology 2014 2014 - 4 citations - Show abstract - Cite 1.7% topic match

1.7%

0.1

2017

[547] Alone No Longer E. Weston Journal Not Provided 2017 - 1 citations - Show abstract - Cite 1.7% topic match

1.7%

0.0

2015

[548] Optimizing Quality of Care for Septic Patients in Developing C. Saleh and J. Saleh https://doi.org/10.15226/2374-684X/2/1/00115 2015 - 0 citations - Show abstract - Cite 1.7% topic match

1.6%

0.0

2023

[549] Artificial Intelligence for Predicting Mortality Due to Sepsis Jee-Woo Choi, ..., and Seung Park 2023 IEEE International Conference on Consumer Electronics (ICCE) 2023 - 0 citations - Show abstract - Cite 1.6% topic match

1.6%

0.7

2012

[550] Challenge : An Artificial Neural Network to Predict Mortality in ICU Patients and Application of Solar Physics Analysis Methods Tom J. Pollard, ..., and Kevin Fong Journal Not Provided 2012 - 9 citations - Show abstract - Cite 1.6% topic match

1.5%

0.2

2005

[551] Research Comparison between logistic regression and neural networks to predict death in patients with suspected sepsis in the emergency Jorge Farbiarz, ..., and F. Jaimes Journal Not Provided 2005 - 3 citations - Show abstract - Cite Abstract: Introduction Neural networks are new methodological tools based on nonlinear models. They appear to be better at prediction and classification in biological systems than do traditional strategies such as logistic regression. This paper provides a practical example that contrasts both approaches within the setting of suspected sepsis in the emergency room. Methods The study population comprised patients with suspected bacterial infection as their main diagnosis for admission to the emergency room at two University-based hospitals. Mortality within the first 28 days from admission was predicted using logistic regression with the following variables: age, immunosuppressive systemic disease, general systemic disease, Shock Index, temperature, respiratory rate, Glasgow Coma Scale score, leucocyte counts, platelet counts and creatinine. Also, with the same input and output variables, a probabilistic neural network was trained with an adaptive genetic algorithm. The network had three neurone layers: 10 neurones in the input layer, 368 in the hidden layer and two in the output layer. Calibration was measured using the Hosmer-Lemeshow goodness-of-fit test and discrimination was determined using receiver operating characteristic curves. Results A total of 533 patients were recruited and overall 28-day mortality was 19%. The factors chosen by logistic regression (with their score in parentheses) were as follows: immunosuppressive systemic disease or general systemic disease (2), respiratory rate 24–33 breaths/min (1), respiratory rate ≥ 34 breaths/min (3), Glasgow Come Scale score ≤12 (3), Shock Index ≥ 1.5 (2) and temperature <38°C (2). The network included all variables and there were no significant differences in predictive ability between the approaches. The areas under the receiver operating characteristic curves were 0.7517 and 0.8782 for the logistic model and the neural network, respectively (P = 0.037). Conclusion A predictive model would be an extremely useful tool in the setting of suspected sepsis in the emergency room. It could serve both as a guideline in medical decision-making and as a simple way to select or stratify patients in clinical research. Our proposed model and the specific development method – either logistic regression or neural networks – must be evaluated and validated in an independent population. 1.5% topic match

1.5%

0.0

2023

[552] Novel AI-based Prediction Approach for Improving Patient Treatment in Healthcare Ramya Thatikonda, ..., and Bibhuprasad Sahu 2023 2nd International Conference on Ambient Intelligence in Health Care (ICAIHC) 2023 - 0 citations - Show abstract - Cite 1.5% topic match

1.5%

16.0

2016

[553] Diagnosing sepsis is subjective and highly variable: a survey of intensivists using case vignettes C. Rhee, ..., and M. Klompas Critical Care 2016 - 133 citations - Show abstract - Cite 1.5% topic match

1.5%

13.2

2016

[554] Multi-task Prediction of Disease Onsets from Longitudinal Laboratory Tests N. Razavian, ..., and D. Sontag Machine Learning in Health Care 2016 - 101 citations - Show abstract - Cite 1.5% topic match

1.5%

0.0

2020

[555] Risk Stratification in Sepsis: What We Can Do in the Emergency Room? Sebastian Dogaru, ..., and F. Purcaru Internal Medicine 2020 - 0 citations - Show abstract - Cite 1.5% topic match

1.5%

0.2

2019

[556] Artificial Intelligence-based tools to control healthcare associated infections: where do we stand A. Scardoni, ..., and A. Odone European Journal of Public Health 2019 - 1 citations - Show abstract - Cite 1.5% topic match

1.5%

30.8

2020

[557] Access to intensive care in 14 European countries: a spatial analysis of intensive care need and capacity in the light of COVID-19 J. Bauer, ..., and D. Groneberg Intensive Care Medicine 2020 - 120 citations - Show abstract - Cite 1.5% topic match

1.5%

0.0

2024

[558] Renal arterial resistive index versus novel biomarkers for the early prediction of sepsis-associated acute kidney injury. Taysser Zaitoun, ..., and Islam Ahmed Internal and emergency medicine 2024 - 0 citations - Show abstract - Cite 1.5% topic match

1.4%

37.0

2015

[559] The Surviving Sepsis Campaign bundles and outcome: results from the International Multicentre Prevalence Study on Sepsis (the IMPreSS study) A. Rhodes, ..., and M. Levy Intensive Care Medicine 2015 - 336 citations - Show abstract - Cite 1.4% topic match

1.4%

1.7

2014

[560] Angiopoietin-1, Angiopoietin-2 and Bicarbonate as Diagnostic Biomarkers in Children with Severe Sepsis Kun Wang, ..., and M. Kirby PLoS ONE 2014 - 17 citations - Show abstract - Cite 1.4% topic match

1.3%

0.2

2013

[561] Actualización del bundle de reanimación inicial y monitorización integral de la perfusión tisular en la sepsis severa P. CarlosRomero and P. GlennHernández Revista Medica De Chile 2013 - 2 citations - Show abstract - Cite 1.3% topic match

1.3%

0.8

2023

[562] The Learning Electronic Health Record. G. Clermont Critical care clinics 2023 - 1 citations - Show abstract - Cite 1.3% topic match

1.3%

1.9

2023

[563] Integrated artificial intelligence and predictive maintenance of electric vehicle components with optical and quantum enhancements P. Rao, ..., and M. Arumugam Optical and Quantum Electronics 2023 - 2 citations - Show abstract - Cite 1.3% topic match

1.2%

23.3

2012

[564] Predicting in-hospital mortality of ICU patients: The PhysioNet/Computing in cardiology challenge 2012 Ikaro Silva, ..., and R. Mark 2012 Computing in Cardiology 2012 - 277 citations - Show abstract - Cite 1.2% topic match

1.1%

0.0

2019

[565] The 35 Annual Workshop on Mathematical Problems in Industry: Data-driven predictive models for healthcare (Iterex group) M. Aminian, ..., and K. Sugita Journal Not Provided 2019 - 0 citations - Show abstract - Cite Abstract: Background. Chronic Obstructive Pulmonary Disease (COPD) and sepsis are two conditions which have enormous health impacts in the United States. COPD refers to a collection of diseases resulting in airflow blockage and breathing problems affecting primarily chronic, long-term smokers. Fifteen million people in the US report they have COPD, and as of 2011 was the third leading cause of death, not to mention the economic costs. Sepsis is a similarly pressing health condition. According to the Mayo Clinic, sepsis is “...a potentially life-threatening condition caused by the body’s response to an infection” and is particularly prevalent in those who are, or have recently been, hospitalized. Sepsis may lead to septic shock, which is a life threatening condition. The Centers for Disease Control report that approximately 1.7 million adults in the US develop sepsis, and accounts for one third of deaths in hospitals. Given these statistics and the failures of traditional approaches to prediction and treatment, it is clear that there are opportunities for improvement. In modern years, the ongoing development of machine learning tools and the maturation of data analysis as a disciplined field have resulted in improvements in state-of-the-art in a wide variety of fields, including healthcare. These approaches have been particularly in their ability to develop predictive models for complex problems for which first-principles modeling may be out of reach, or infeasible in practice. For these reasons, Iterex has motivated our group at MPI 2019 to develop data-driven approaches to early prediction and triage decisionis related to sepsis and COPD. In the context of the workshop, we were provided with two data sets related to each condition. With the provided COPD data set, our main objective was to accurately predict exacerbation events, while in the case of sepsis, patient time series were provided and the goal was to predict the onset of sepsis. We discuss our key findings for the two data sets in the paragraphs below. 1.1% topic match

1.1%

0.7

2017

[566] Harnessing the power of artificial intelligence. J. Sensmeier Nursing management 2017 - 5 citations - Show abstract - Cite 1.1% topic match

1.1%

0.3

2021

[567] Prediction of Resuscitation for Pediatric Sepsis from Data Available at Triage P. Stella, ..., and Yindalon Aphinyanagphongs AMIA ... Annual Symposium proceedings. AMIA Symposium 2021 - 1 citations - Show abstract - Cite 1.1% topic match

1.1%

7.0

2023

[568] The impact of inconsistent human annotations on AI driven clinical decision making Aneeta Sylolypavan, ..., and M. Sim NPJ Digital Medicine 2023 - 10 citations - Show abstract - Cite 1.1% topic match

1.1%

2.4

2023

[569] Can artificial intelligence predict COVID-19 mortality? A. C. Genç, ..., and S. Yaylaci European review for medical and pharmacological sciences 2023 - 2 citations - Show abstract - Cite 1.1% topic match

1.1%

1.0

2020

[570] Predicting Early Neonatal Sepsis using Neural Networks and Other Classifiers Redwan Hasif Alvi, ..., and R. Rahman 2020 IEEE 10th International Conference on Intelligent Systems (IS) 2020 - 4 citations - Show abstract - Cite 1.1% topic match

1.0%

0.0

2023

[571] Early Prediction of Sepsis Using Time Series Forecasting Jinghua Xu, ..., and Stefan Riezler 2023 IEEE 19th International Conference on e-Science (e-Science) 2023 - 0 citations - Show abstract - Cite 1.0% topic match

1.0%

0.0

2023

[572] ARTIFICIAL INTELLIGENCE ENABLED INTERNET OF MEDICAL THINGS (IOMT) TECHNIQUES AND METHODS Hani A. Harb Journal of Advance Research in Computer Science & Engineering (ISSN: 2456-3552) 2023 - 0 citations - Show abstract - Cite 1.0% topic match

1.0%

0.0

2012

[573] Real-time polymerase chain reaction to evaluate antibiotic appropriateness : Should we spread the news to multiply it ? * Editorials Journal Not Provided 2012 - 0 citations - Show abstract - Cite Abstract: Crit Care Med 2012 Vol. 40, No. 8 Sepsis is a major cause of death in intensive care units (ICUs) worldwide, with mortality rates ranging from 20% for sepsis, through 40% for severe sepsis, to over 60% for septic shock. Sepsis accounts for as much as 25% of ICU bed utilization (1, 2). A proven or suspected infection is a conditio sine qua non to diagnose sepsis. However, in contrast to earlier definitions, blood stream infections with a causative microorganism are no longer essential (3). The treatment of infections is founded on principles of appropriate drug selection for both empiric and targeted (final) therapy, based on suspected susceptibility patterns for the causative pathogen (4). Selection of the initial antibiotic treatment is often made empirically. The appropriateness of the initial choice can be evaluated when Gram stains and/or culture results with information on susceptibility of the causative pathogen(s) become available. This information can lead to changes in antibiotic regimen; if the initial therapy was inadequate, the delay (during which the infection was either not treated with effective antibiotics or suboptimally treated with partly susceptible microorganisms) may affect outcome. Inappropriate antimicrobial therapy has been identified as an independent factor contributing to mortality in sepsis. Rates varying from 15% to 30% of inappropriate empiric antimicrobial therapy have been reported (5–7). Not only appropriateness of antibiotic therapy but also timing has been shown to be of paramount importance in critically ill patients. Early adequate antibacterial treatment in septic shock patients is essential, as mortality increases by 7.6% each hour of delay after onset of hypotension (8). Also in candidemia both inappropriate and delayed therapy have been proven to negatively affect outcome (9, 10). Various risk factors that may contribute to inappropriate antimicrobial treatment have been identified. These include recent exposure to antibiotics, use of broad-spectrum antibiotics, prolonged length of stay, prolonged mechanical ventilation, and presence of invasive devices (11). Several interventions can be used to decrease the risk of inappropriate choice of antibiotics. These include measures such as the use of antibiotic practice guidelines, consulting an infectious disease specialist or microbiologist, and implementing more rapid methods of microbiological identification (12). Furthermore, intensivists should be familiar with the pathogens most frequently involved in community-acquired and nosocomial infections encountered in their ICU. Initiation of (empirical) antibiotic treatment based on this knowledge as well as individual patient characteristics will increase the likelihood of initiating the right therapy. In many cases this will require initial treatment with broad-spectrum antibiotics, which can be changed when the culture results are known. Real-time polymerase chain reaction (PCR), also called quantitative real-time polymerase chain reaction (qPCR), is a laboratory technique based on PCR, which is used to amplify and simultaneously quantify nucleic acids or targeted DNA molecules. For specific sequences in a DNA sample, qPCR enables both detection and quantification (13). After initial application in viral diseases to quantify viral load, qPCR has evolved to both identify nucleic acid sequences of many bacteria or fungi enabling rapid detection of causative pathogens and provide information on the quantity reflecting bacterial or fungal load. Multiplex PCR assays are able to detect various pathogens in blood samples of sepsis patients (DNAemia) within hours, facilitating earlier optimal therapy. It was calculated that 36.4 (confidence interval 22–51) days of early inadequate treatment could be eliminated per 100 PCR tests performed in the ICU if rapidly available PCR results were used to adjust antimicrobial therapy (14). It could be hypothesized that effect of therapy can be monitored by repeated qPCRs, assuming rapid reduction of bacterial load due to appropriate antimicrobial therapy. In fact qPCR potentially may provide information on antibiotic appropriateness before culture results are available. In this issue of Critical Care Medicine, Chuang and colleagues (15) evaluate repeated qPCR assays to study bacterial load in 51 ICU patients with cultureproven Acinetobacter baumannii bacteremia in order to assess antibiotic appropriateness. The authors were first to show that qPCR can be used to study the antibiotic appropriateness in critically ill bacteremic patients and its effects on outcome. They demonstrated that immunosuppressants were an independent predictor for slower bacterial clearance and appropriate antibiotic usage was an independent predictor for more rapid bacterial clearance. Patients with a slower rate of bacterial clearance experienced higher in-hospital mortality (odds ratio, 2.323; p = .04). The rate of bacterial clearance served as a timely surrogate marker for evaluating the appropriateness of antibiotics in this patient group. qPCR poses several advantages over conventional culture techniques. It can detect less than five copies of a pathogenspecific target sequence within hours, making it possible to rapidly analyze small samples and low numbers of pathogens and quantify them with low variation coefficients. This provides benefit in particular in infections with pathogens difficult to routinely culture or with slow growth. Furthermore, after administration of antibiotics, nucleic acids even from dead pathogens still can be detected (16). This information could lead to early institution of effective infection prevention measures, reduced cross-contamination *See also p. 2273. 1.0% topic match

0.9%

0.0

2023

[574] Predictive Modeling Using Artificial Intelligence and Machine Learning Algorithms on Electronic Health Record Data: Advantages and Challenges. Michael J. Patton and V. Liu Critical care clinics 2023 - 0 citations - Show abstract - Cite 0.9% topic match

0.9%

1.6

2021

[575] Development and internal validation of a simple prognostic score for early sepsis risk stratification in the emergency department Bofu Liu, ..., and Yu Cao BMJ Open 2021 - 5 citations - Show abstract - Cite 0.9% topic match

0.9%

1.6

2010

[576] Clinical biomarkers in sepsis. R. Anderson and René Schmidt Frontiers in bioscience 2010 - 23 citations - Show abstract - Cite 0.9% topic match

0.8%

15.2

2023

[577] Artificial intelligence enhanced sensors - enabling technologies to next-generation healthcare and biomedical platform Chan Wang, ..., and Chengkuo Lee Bioelectronic Medicine 2023 - 15 citations - Show abstract - Cite 0.8% topic match

0.8%

2.1

2023

[578] Predictability performance of urinary C–C motif chemokine ligand 14 and renal resistive index for persistent sepsis-associated acute kidney injury in ICU patients Wei Jiang, ..., and R. Zheng International Urology and Nephrology 2023 - 3 citations - Show abstract - Cite 0.8% topic match

0.8%

4.4

2013

[579] Diagnostic and prognostic markers in sepsis J. Vincent and M. Beumier Expert Review of Anti-infective Therapy 2013 - 50 citations - Show abstract - Cite 0.8% topic match

0.8%

5.9

2020

[580] A Predictive Model Based on Machine Learning for the Early Detection of Late-Onset Neonatal Sepsis: Development and Observational Study Wongeun Song, ..., and Sooyoung Yoo JMIR Medical Informatics 2020 - 24 citations - Show abstract - Cite 0.8% topic match

0.8%

0.2

2016

[581] Current management of sepsis and septic shock J. Vincent Signa Vitae 2016 - 2 citations - Show abstract - Cite 0.8% topic match

0.7%

0.0

2022

[582] Entropy Analysis of Total Respiratory Time Series for Sepsis Detection Hugo Sousa, ..., and T. Henriques 2022 E-Health and Bioengineering Conference (EHB) 2022 - 0 citations - Show abstract - Cite 0.7% topic match

0.7%

0.3

2006

[583] Sepsis, septic shock and multiple organ failure Sanjay Gupta and M. Jonas Anaesthesia & Intensive Care Medicine 2006 - 6 citations - Show abstract - Cite 0.7% topic match

0.7%

0.3

2011

[584] Guidelines for the treatment of severe sepsis and septic shock: hemodynamic resuscitation. G. Westphal, ..., and F. Machado Revista Brasileira de terapia intensiva 2011 - 4 citations - Show abstract - Cite 0.7% topic match

0.7%

0.3

2020

[585] Future of the Artificial Intelligence in Daily Health Applications Melis Y. Minas and Giorgos Triantafillou The European Journal of Social & Behavioural Sciences 2020 - 1 citations - Show abstract - Cite 0.7% topic match

0.7%

7.9

2019

[586] Self-attention based recurrent convolutional neural network for disease prediction using healthcare data Mohd Usama, ..., and G. Muhammad Computer methods and programs in biomedicine 2019 - 37 citations - Show abstract - Cite 0.7% topic match

0.7%

0.6

2021

[587] Early prediction of survival at different time intervals in sepsis patients: A visualized prediction model with nomogram and observation study Shih-Hong Chen, ..., and Y. Yeh Tzu-Chi Medical Journal 2021 - 2 citations - Show abstract - Cite 0.7% topic match

0.7%

0.0

2020

[588] MEASURING CHANGE: PREDICTION OF EARLY ONSET SEPSIS Aric Schadler https://doi.org/10.13023/ETD.2020.393 2020 - 0 citations - Show abstract - Cite 0.7% topic match

0.6%

0.0

1997

[589] What is new in sepsis therapy? Reinhart and Karzai Acta Anaesthesiologica Scandinavica 1997 - 0 citations - Show abstract - Cite 0.6% topic match

0.6%

0.6

2021

[590] Ambulatory Risk Models for the Long-Term Prevention of Sepsis: Retrospective Study Jewel Y Lee, ..., and J. Hadlock JMIR Medical Informatics 2021 - 2 citations - Show abstract - Cite 0.6% topic match

0.6%

0.5

2022

[591] Harnessing AI in sepsis care David W. Bates and Ania Syrowatka Nature Medicine 2022 - 1 citations - Show abstract - Cite 0.6% topic match

0.5%

5.8

2021

[592] Preventing sepsis; how can artificial intelligence inform the clinical decision-making process? A systematic review N. Hassan, ..., and S. Slight International journal of medical informatics 2021 - 19 citations - Show abstract - Cite 0.5% topic match

0.5%

0.1

2013

[593] [Initial resuscitation bundle and monitoring tissue perfusion in severe sepsis]. Carlos Romero P and Glenn Hernández P Revista medica de Chile 2013 - 1 citations - Show abstract - Cite 0.5% topic match

0.5%

0.7

2020

[594] Improvements in Patient Monitoring in the Intensive Care Unit: Survey Study (Preprint) A. Poncette, ..., and F. Balzer https://doi.org/10.2196/preprints.19091 2020 - 3 citations - Show abstract - Cite Abstract: BACKGROUND Due to demographic change and, more recently, coronavirus disease (COVID-19), the importance of modern intensive care units (ICU) is becoming apparent. One of the key components of an ICU is the continuous monitoring of patients' vital parameters. However, existing advances in informatics, signal processing, or engineering that could alleviate the burden on ICUs have not yet been applied. This could be due to the lack of user involvement in research and development. OBJECTIVE This study focused on the satisfaction of ICU staff with current patient monitoring and their suggestions for future improvements. We aimed to identify aspects of monitoring that interrupt patient care, display devices for remote monitoring, use cases for artificial intelligence (AI), and whether ICU staff members are willing to improve their digital literacy or contribute to the improvement of patient monitoring. We further aimed to identify differences in the responses of different professional groups. METHODS This survey study was performed with ICU staff from 4 ICUs of a German university hospital between November 2019 and January 2020. We developed a web-based 36-item survey questionnaire, by analyzing a preceding qualitative interview study with ICU staff, about the clinical requirements of future patient monitoring. Statistical analyses of questionnaire results included median values with their bootstrapped 95% confidence intervals, and chi-square tests to compare the distributions of item responses of the professional groups. RESULTS In total, 86 of the 270 ICU physicians and nurses completed the survey questionnaire. The majority stated they felt confident using the patient monitoring equipment, but that high rates of false-positive alarms and the many sensor cables interrupted patient care. Regarding future improvements, respondents asked for wireless sensors, a reduction in the number of false-positive alarms, and hospital standard operating procedures for alarm management. Responses to the display devices proposed for remote patient monitoring were divided. Most respondents indicated it would be useful for earlier alerting or when they were responsible for multiple wards. AI for ICUs would be useful for early detection of complications and an increased risk of mortality; in addition, the AI could propose guidelines for therapy and diagnostics. Transparency, interoperability, usability, and staff training were essential to promote the use of AI. The majority wanted to learn more about new technologies for the ICU and required more time for learning. Physicians had fewer reservations than nurses about AI-based intelligent alarm management and using mobile phones for remote monitoring. CONCLUSIONS This survey study of ICU staff revealed key improvements for patient monitoring in intensive care medicine. Hospital providers and medical device manufacturers should focus on reducing false alarms, implementing hospital alarm standard operating procedures, introducing wireless sensors, preparing for the use of AI, and enhancing the digital literacy of ICU staff. Our results may contribute to the user-centered transfer of digital technologies into practice to alleviate challenges in intensive care medicine. CLINICALTRIAL ClinicalTrials.gov NCT03514173; https://clinicaltrials.gov/ct2/show/NCT03514173 0.5% topic match

0.5%

0.0

2020

[595] Sepsis and septic shock - recognize early, act fast, treat right V. Bumbaširević, ..., and N. Ivancević Srpski arhiv za celokupno lekarstvo 2020 - 0 citations - Show abstract - Cite 0.5% topic match

0.5%

2.6

2021

[596] Mechanical Learning for Prediction of Sepsis-Associated Encephalopathy Lina Zhao, ..., and Yi Li Frontiers in Computational Neuroscience 2021 - 7 citations - Show abstract - Cite 0.5% topic match

0.5%

38.2

2023

[597] Drawbacks of Artificial Intelligence and Their Potential Solutions in the Healthcare Sector Bangul Khan, ..., and Saad Abdullah Biomedical Materials & Devices (New York, N.y.) 2023 - 56 citations - Show abstract - Cite 0.5% topic match

0.5%

2.3

2014

[598] A Multiscale Entropy-Based Tool for Scoring Severity of Systemic Inflammation* B. Vandendriessche, ..., and A. Cauwels Critical Care Medicine 2014 - 23 citations - Show abstract - Cite 0.5% topic match

0.4%

0.9

2018

[599] Prehospital antibiotics for sepsis: beyond mortality? V. M. Quinten, ..., and J. T. ter Maaten The Lancet. Respiratory medicine 2018 - 6 citations - Show abstract - Cite 0.4% topic match

0.4%

0.6

2021

[600] Prediction of Sudden Health Crises Owing to Congestive Heart Failure with Deep Learning Models S. Shabbeer and E. Reddy Rev. d'Intelligence Artif. 2021 - 2 citations - Show abstract - Cite 0.4% topic match

0.4%

0.0

2023

[601] Machine-Based Algorithm: A Revolution We Need For Early Sepsis Diagnosis In Hospitals. Muhammad Usama Shahid, ..., and Syeda Zainab Fatima JPMA. The Journal of the Pakistan Medical Association 2023 - 0 citations - Show abstract - Cite 0.4% topic match

0.4%

0.1

2010

[602] Prediction about severity and outcome of sepsis by proatrial Ruilan Wang and Fu-xin Kang Chinese journal of traumatology 2010 - 1 citations - Show abstract - Cite 0.4% topic match

0.4%

0.0

2022

[603] ALRt: An Active Learning Framework for Irregularly Sampled Temporal Data Ronald Moore and Rishikesan Kamaleswaran ArXiv 2022 - 0 citations - Show abstract - Cite - PDF 0.4% topic match

0.3%

3.7

2017

[604] How much data should we collect? A case study in sepsis detection using deep learning F. van Wyk, ..., and R. Davis 2017 IEEE Healthcare Innovations and Point of Care Technologies (HI-POCT) 2017 - 25 citations - Show abstract - Cite 0.3% topic match

0.3%

0.0

2023

[605] Artificial intelligence: do we really need it in pulmonary function interpretation? I. Steenbruggen and M. McCormack European Respiratory Journal 2023 - 0 citations - Show abstract - Cite 0.3% topic match

0.3%

0.0

2018

[606] Early and adequate empirical antibiotic treatment in sepsis saves lives , but how should it be provided ? La administración precoz y adecuada de la antibioticoterapia empírica en la sepsis salva vidas ; pero ¿ cómo hacerlo ? E. Piacentini and R. Ferrer Journal Not Provided 2018 - 0 citations - Show abstract - Cite 0.3% topic match

0.3%

1178.6

2017

[607] A survey on deep learning in medical image analysis G. Litjens, ..., and C. I. Sánchez Medical image analysis 2017 - 8761 citations - Show abstract - Cite - PDF 0.3% topic match

0.3%

0.0

2016

[608] Implementation of “CODE SEPSIS” for septic patients at Al Wakra Hospital: A practice improvement initiative H. Abdel-Aziz, ..., and M. Heidous Journal of emergency medicine, trauma and acute care 2016 - 0 citations - Show abstract - Cite 0.3% topic match

0.3%

33.1

2018

[609] Big Data and Data Science in Critical Care. MD L. Nelson Sanchez-Pinto, ..., and MD Matthew M. Churpek Chest 2018 - 190 citations - Show abstract - Cite 0.3% topic match

0.3%

0.4

2019

[610] Artificial Intelligence Perspective on Healthcare R. Rayan PsychRN: Psycho-Educational Intervention (Topic) 2019 - 2 citations - Show abstract - Cite 0.3% topic match

0.3%

1.3

2022

[611] Identifying high-risk phenotypes and associated harms of delayed time-to-antibiotics in patients with ICU onset sepsis: A retrospective cohort study. Wenhan Hu, ..., and Ying-chun Huang Journal of critical care 2022 - 2 citations - Show abstract - Cite 0.3% topic match

0.2%

26.8

2023

[612] Algorithmic fairness in artificial intelligence for medicine and healthcare Richard J. Chen, ..., and Faisal Mahmood Nature Biomedical Engineering 2023 - 31 citations - Show abstract - Cite 0.2% topic match

0.2%

19.2

1964

[613] SEPTIC SHOCK Edward D. Frank International Anesthesiology Clinics 1964 - 1161 citations - Show abstract - Cite 0.2% topic match

0.2%

2.4

2017

[614] Predicting Severe Sepsis Using Text from the Electronic Health Record Phil Culliton, ..., and S. I. Gallant ArXiv 2017 - 16 citations - Show abstract - Cite - PDF 0.2% topic match

0.2%

2.2

2023

[615] An AI-powered patient triage platform for future viral outbreaks using COVID-19 as a disease model G. Charkoftaki, ..., and V. Vasiliou Human Genomics 2023 - 2 citations - Show abstract - Cite 0.2% topic match

0.2%

0.4

2021

[616] A Methodology for a Scalable, Collaborative, and Resource-Efficient Platform to Facilitate Healthcare AI Research R. Y. Cohen and V. Kovacheva ArXiv 2021 - 1 citations - Show abstract - Cite - PDF 0.2% topic match

0.1%

24.6

2021

[617] Accessing Artificial Intelligence for Clinical Decision-Making C. Giordano, ..., and P. Tighe Frontiers in Digital Health 2021 - 76 citations - Show abstract - Cite Abstract: Advancements in computing and data from the near universal acceptance and implementation of electronic health records has been formative for the growth of personalized, automated, and immediate patient care models that were not previously possible. Artificial intelligence (AI) and its subfields of machine learning, reinforcement learning, and deep learning are well-suited to deal with such data. The authors in this paper review current applications of AI in clinical medicine and discuss the most likely future contributions that AI will provide to the healthcare industry. For instance, in response to the need to risk stratify patients, appropriately cultivated and curated data can assist decision-makers in stratifying preoperative patients into risk categories, as well as categorizing the severity of ailments and health for non-operative patients admitted to hospitals. Previous overt, traditional vital signs and laboratory values that are used to signal alarms for an acutely decompensating patient may be replaced by continuously monitoring and updating AI tools that can pick up early imperceptible patterns predicting subtle health deterioration. Furthermore, AI may help overcome challenges with multiple outcome optimization limitations or sequential decision-making protocols that limit individualized patient care. Despite these tremendously helpful advancements, the data sets that AI models train on and develop have the potential for misapplication and thereby create concerns for application bias. Subsequently, the mechanisms governing this disruptive innovation must be understood by clinical decision-makers to prevent unnecessary harm. This need will force physicians to change their educational infrastructure to facilitate understanding AI platforms, modeling, and limitations to best acclimate practice in the age of AI. By performing a thorough narrative review, this paper examines these specific AI applications, limitations, and requisites while reviewing a few examples of major data sets that are being cultivated and curated in the US. 0.1% topic match

0.1%

1.4

2001

[618] Cluster Headache after Dental Extraction: Implications for the Pathogenesis of Cluster Headache? Peter Sörös, ..., and S. Evers Cephalalgia 2001 - 33 citations - Show abstract - Cite 0.1% topic match

0.1%

119.8

2020

[619] The Machine‐Learning Approach No author found Machine Learning for iOS Developers 2020 - 531 citations - Show abstract - Cite 0.1% topic match

0.1%

4.5

2021

[620] Machine learning methods to improve bedside fluid responsiveness prediction in severe sepsis or septic shock: an observational study. B. Bataille, ..., and Pierre Cocquet British journal of anaesthesia 2021 - 16 citations - Show abstract - Cite 0.1% topic match

0.1%

2.4

2023

[621] Machine learning in clinical practice: Evaluation of an artificial intelligence tool after implementation H. Akhlaghi, ..., and Bahman Tahayori Emergency Medicine Australasia 2023 - 2 citations - Show abstract - Cite 0.1% topic match

0.1%

16.0

2021

[622] Interpretable deep learning model for building energy consumption prediction based on attention mechanism Yuan Gao and Yingjun Ruan Energy and Buildings 2021 - 47 citations - Show abstract - Cite 0.1% topic match

0.1%

1.4

2023

[623] End-to-end learning with interpretation on electrohysterography data to predict preterm birth Anne Fischer, ..., and M. Hoogendoorn Computers in biology and medicine 2023 - 2 citations - Show abstract - Cite 0.1% topic match

0.1%

3.6

2022

[624] Cost-effectiveness of using artificial intelligence versus polygenic risk score to guide breast cancer screening S. Mital and H. V. Nguyen BMC Cancer 2022 - 8 citations - Show abstract - Cite 0.1% topic match

0.1%

1.4

2022

[625] Detecting sepsis from photoplethysmography: strategies for dataset preparation S. Lombardi, ..., and L. Bocchi 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) 2022 - 3 citations - Show abstract - Cite 0.1% topic match

0.1%

158.8

2016

[626] Flow The Psychology Of Optimal Experience Nicole Fruehauf Journal Not Provided 2016 - 1361 citations - Show abstract - Cite 0.1% topic match

0.1%

0.0

2023

[627] Sepsis Treatment Recommendation Using Sensitivity to Input Medicine Dosage in Deep Neural Networks Eu-Tteum Baek Applied Sciences 2023 - 0 citations - Show abstract - Cite 0.1% topic match

0.1%

8.4

2021

[628] New Microbiological Techniques for the Diagnosis of Bacterial Infections and Sepsis in ICU Including Point of Care A. Peri, ..., and P. Harris Current Infectious Disease Reports 2021 - 26 citations - Show abstract - Cite 0.1% topic match

0.1%

3043.4

2016

[629] Case Study Research Design And Methods C. Nadel Journal Not Provided 2016 - 26080 citations - Show abstract - Cite 0.1% topic match

0.0%

1.9

2020

[630] Towards the use of vector based GP to predict physiological time series Irene Azzali, ..., and M. Giacobini Appl. Soft Comput. 2020 - 8 citations - Show abstract - Cite 0.0% topic match

0.0%

3.0

2012

[631] Open by default: a proposed copyright license and waiver agreement for open access research and data in peer-reviewed journals I. Hrynaszkiewicz and M. Cockerill BMC Research Notes 2012 - 36 citations - Show abstract - Cite 0.0% topic match

0.0%

0.0

2023

[632] Children are small adults (when properly normalized): Transferrable/generalizable sepsis prediction BA Caitlin Marassi, ..., and O. Articleinf Surgery Open Science 2023 - 0 citations - Show abstract - Cite 0.0% topic match

0.0%

2.9

1977

[633] Program Behavior: Models and Measurements J. R. Spirn Journal Not Provided 1977 - 137 citations - Show abstract - Cite 0.0% topic match

0.0%

2.6

2013

[634] Factors that affect sleep quality: perceptions made by patients in the intensive care unit after thoracic surgery Lei Zhang, ..., and Changli Wang Supportive Care in Cancer 2013 - 30 citations - Show abstract - Cite 0.0% topic match

0.0%

0.0

2020

[635] Towards early sepsis detection from measurements at the general ward through deep learning (Preprint) S. P. Oei, ..., and M. Mischi https://doi.org/10.2196/preprints.18968 2020 - 0 citations - Show abstract - Cite 0.0% topic match

0.0%

1.8

2020

[636] Acute Hypertensive Episodes Prediction Nevo Itzhak, ..., and Robert Moskovitch Conference on Artificial Intelligence in Medicine in Europe 2020 - 8 citations - Show abstract - Cite 0.0% topic match

0.0%

385.7

2016

[637] Applied Missing Data Analysis S. Eberhart Journal Not Provided 2016 - 3305 citations - Show abstract - Cite 0.0% topic match

0.0%

0.0

2024

[638] Optimal Treatment Strategies for Critical Patients with Deep Reinforcement Learning Simi Job, ..., and Qing Li ACM Transactions on Intelligent Systems and Technology 2024 - 0 citations - Show abstract - Cite 0.0% topic match

0.0%

0.0

2024

[639] Establishing a Center for Innovation and Artificial Intelligence in a Tertiary Medical Center: Successes and Challenges. Nadav Loebl, ..., and L. Perl The Israel Medical Association journal : IMAJ 2024 - 0 citations - Show abstract - Cite 0.0% topic match

0.0%

0.0

2019

[640] Feature engineering combined with 1-D convolutional neural network for improved mortality prediction Rohit Verma, ..., and A. Shukla Bio-Algorithms and Med-Systems 2019 - 0 citations - Show abstract - Cite - PDF Abstract: Abstract Objectives The appropriate care for patients admitted in Intensive care units (ICUs) is becoming increasingly prominent, thus recognizing the use of machine learning models. The real-time prediction of mortality of patients admitted in ICU has the potential for providing the physician with the interpretable results. With the growing crisis including soaring cost, unsafe care, misdirected care, fragmented care, chronic diseases and evolution of epidemic diseases in the domain of healthcare demands the application of automated and real-time data processing for assuring the improved quality of life. The intensive care units (ICUs) are responsible for generating a wealth of useful data in the form of Electronic Health Record (EHR). This data allows for the development of a prediction tool with perfect knowledge backing. Method We aimed to build the mortality prediction model on 2012 Physionet Challenge mortality prediction database of 4,000 patients admitted in ICU. The challenges in the dataset, such as high dimensionality, imbalanced distribution and missing values, were tackled with analytical methods and tools via feature engineering and new variable construction. The objective of the research is to utilize the relations among the clinical variables and construct new variables which would establish the effectiveness of 1-Dimensional Convolutional Neural Network (1-D CNN) with constructed features. Results Its performance with the traditional machine learning algorithms like XGBoost classifier, Light Gradient Boosting Machine (LGBM) classifier, Support Vector Machine (SVM), Decision Tree (DT), K-Neighbours Classifier (K-NN), and Random Forest Classifier (RF) and recurrent models like Long Short-Term Memory (LSTM) and LSTM-attention is compared for Area Under Curve (AUC). The investigation reveals the best AUC of 0.848 using 1-D CNN model. Conclusion The relationship between the various features were recognized. Also, constructed new features using existing ones. Multiple models were tested and compared on different metrics. 0.0% topic match

Share this report with colleagues?

Introduce your friends to deep search. Help accelerate research discovery.

Research Topic

Summary

References

Select the format you want to download:

Download Citations

Citation Text

BibTeX

RIS

Download Citations

Citation Text

BibTeX

RIS

Download Citations

Citation Text

BibTeX

RIS

Download Citations

Citation Text

BibTeX

RIS

Download Citations

Citation Text

BibTeX

RIS

Download Citations

Citation Text

BibTeX

RIS

Download Citations

Citation Text

BibTeX

RIS

Download Citations

Citation Text

BibTeX

RIS

Download Citations

Citation Text

BibTeX

RIS

Download Citations

Citation Text

BibTeX

RIS

Download Citations

Citation Text

BibTeX

RIS

Download Citations

Citation Text

BibTeX

RIS

Download Citations

Citation Text

BibTeX

RIS

Download Citations

Citation Text

BibTeX

RIS

Download Citations

Citation Text

BibTeX

RIS

Download Citations

Citation Text

BibTeX

RIS

Download Citations

Citation Text

BibTeX

RIS

Download Citations

Citation Text

BibTeX

RIS

Download Citations

Citation Text

BibTeX

RIS