Next Article in Journal
Impact of the Different Corneal Storage Flasks on Endothelial Cell Loss During Cultivation—A Retrospective Analysis
Previous Article in Journal
The Impact of Non-Coding RNA on Inflammation and Airway Remodeling in Asthma Related to Obesity: State-of-the-Art and Therapeutic Perspectives
Previous Article in Special Issue
Artificial Intelligence in Anesthesia: Enhancing Precision, Safety, and Global Access Through Data-Driven Systems
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
JCM
Volume 14
Issue 20
10.3390/jcm14207163
jcm-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

Interpretable Machine Learning Model Integrating Electrocardiographic and Acute Physiology Metrics for Mortality Prediction in Critical Ill Patients

by
Qiuyu Wang
1,2,†,
Bin Wang
1,†,
Bo Chen
1,
Qing Li
1,2,
Yutong Zhao
1,2,
Tianshan Dong
3,
Yifei Wang
1,2,* and
Ping Zhang
1,2,*
1
School of Clinical Medicine, Tsinghua University, Haidian District, Beijing 100084, China
2
Department of Cardiology, Beijing Tsinghua Changgung Hospital, Tsinghua Medicine, Tsinghua University, Beijing 102218, China
3
School of Astronautics, Beihang University, Haidian District, Beijing 100191, China
*
Authors to whom correspondence should be addressed.
†
The authors contributed equally to this work.
J. Clin. Med. 2025, 14(20), 7163; https://doi.org/10.3390/jcm14207163 (registering DOI)
Submission received: 18 August 2025 / Revised: 20 September 2025 / Accepted: 9 October 2025 / Published: 11 October 2025
(This article belongs to the Special Issue New Insights into Critical Care)
Versions Notes

Abstract

Background: Critically ill patients in the intensive care unit (ICU) are characterized by complex comorbidities and a high risk of short-term mortality. Traditional severity scoring systems rely on physiological and laboratory variables but lack direct integration of electrocardiogram (ECG) data. This study aimed to construct an interpretable machine learning (ML) model combining ECG-derived and clinical variables to predict 28-day mortality in ICU patients. Methods: A retrospective cohort analysis was performed with data from the MIMIC-IV v2.2 database. The primary outcome was 28-day mortality. An ECG-based risk score was generated from the first ECG after ICU admission using a deep residual convolutional neural network. Feature selection was guided by XGBoost importance ranking, SHapley Additive exPlanations, and clinical relevance. A three-variable model comprising ECG score, APS-III score, and age (termed the E3A score) was developed and evaluated across four ML algorithms. We evaluated model performance by calculating the AUC of ROC curves, examining calibration, and applying decision curve analysis. Results: A total of 18,256 ICU patients were included, with 2412 deaths within 28 days. The ECG score was significantly higher in non-survivors than in survivors (median [IQR]: 24.4 [15.6–33.4] vs. 13.5 [7.2–22.1], p < 0.001). Logistic regression demonstrated the best discrimination for the E3A score, achieving an AUC of 0.806 (95% CI: 0.784–0.826) for the test set and 0.804 (95% CI: 0.772–0.835) for the validation set. Conclusions: Integrating ECG-derived features with clinical variables improves prognostic accuracy for 28-day mortality prediction in ICU patients, supporting early risk stratification in critical care.
Keywords: electrocardiogram; multimodal clinical data; machine learning; mortality risk prediction; intensive care unit electrocardiogram; multimodal clinical data; machine learning; mortality risk prediction; intensive care unit

Share and Cite

MDPI and ACS Style

Wang, Q.; Wang, B.; Chen, B.; Li, Q.; Zhao, Y.; Dong, T.; Wang, Y.; Zhang, P. Interpretable Machine Learning Model Integrating Electrocardiographic and Acute Physiology Metrics for Mortality Prediction in Critical Ill Patients. J. Clin. Med. 2025, 14, 7163. https://doi.org/10.3390/jcm14207163

AMA Style

Wang Q, Wang B, Chen B, Li Q, Zhao Y, Dong T, Wang Y, Zhang P. Interpretable Machine Learning Model Integrating Electrocardiographic and Acute Physiology Metrics for Mortality Prediction in Critical Ill Patients. Journal of Clinical Medicine. 2025; 14(20):7163. https://doi.org/10.3390/jcm14207163

Chicago/Turabian Style

Wang, Qiuyu, Bin Wang, Bo Chen, Qing Li, Yutong Zhao, Tianshan Dong, Yifei Wang, and Ping Zhang. 2025. "Interpretable Machine Learning Model Integrating Electrocardiographic and Acute Physiology Metrics for Mortality Prediction in Critical Ill Patients" Journal of Clinical Medicine 14, no. 20: 7163. https://doi.org/10.3390/jcm14207163

APA Style

Wang, Q., Wang, B., Chen, B., Li, Q., Zhao, Y., Dong, T., Wang, Y., & Zhang, P. (2025). Interpretable Machine Learning Model Integrating Electrocardiographic and Acute Physiology Metrics for Mortality Prediction in Critical Ill Patients. Journal of Clinical Medicine, 14(20), 7163. https://doi.org/10.3390/jcm14207163

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop