Development and validation of an interpretable machine-learning-based model incorporating time-weighted variables for predicting intensive care unit mortality in patients with cardiac arrest: A retrospective study
Intelligent Medicine · 2026-10 · 6 (5) · 495-507
DOI: 10.1016/j.imed.2026.07.004 ↗Kurz gefasst
Fachartikel in der Zeitschrift Intelligent Medicine, 2026-10. Verfasst von Guyu Zhang und 6 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Themen: Intensivpflege, Reanimation
Abstract (Originalsprache)
Background
Cardiac arrest (CA) remains a critical medical emergency characterized by high mortality rates despite advancements in resuscitation and intensive care. The heterogeneous and evolving clinical course of CA patients hinders early and accurate prognostication. This study aimed to construct and externally validate a predictive model for 28-day intensive care unit (ICU) mortality in CA patients by leveraging time-weighted clinical data and traditional as well as machine-learning approaches including Extreme Gradient Boosting (XGBoost), Gradient Boosting with Component-wise Linear Models (Glmboost), random forest (RF), Generalized Linear Models with Elastic Net Regularization (Glmnet), and multivariate Cox regression.
Methods
We retrospectively analyzed adult patients with CA from three large-scale ICU databases: eICU Collaborative Research Database (eICU-CRD) (training cohort, n =1,077), Medical Information Mart for Intensive Care IV (MIMIC-IV v3.1), and MIMIC-III Clinical Database CareVue subset v1.4 (combined validation cohort, n =368). Time-weighted averages (TWA) of clinical parameters—including the Glasgow Coma Scale (GCS), vital signs, and arterial blood gas indices—were computed over the first three ICU days. Variable selection was performed using the least absolute shrinkage and selection operator (LASSO) regression, followed by multivariable Cox regression analysis. Five prognostic models—Glmboost, XGBoost, RF, Glmnet, and Cox regression—were developed and evaluated using C-index, time-dependent area under the curve (AUC), Graf score, and decision curve analysis (DCA). Model interpretability and time-varying effects were examined via SHapley Additive exPlanations (SHAP) and the Piece-wise exponential additive mixed model (PAMM).
Results
Nine independent predictors of ICU mortality were identified, with time-weighted average Glasgow Coma Scale (TWA-GCS) (hazard ratio: 0.75, 95% CI: 0.71–0.78, P 10) TWA-GCS scores, respectively (P
Zitieren
APA
Zhang, G., An, L., Hang, C., Wang, X., Shao, R., Shan, Z., & Tang, Z. (2026). Development and validation of an interpretable machine-learning-based model incorporating time-weighted variables for predicting intensive care unit mortality in patients with cardiac arrest: A retrospective study. Intelligent Medicine, 6(5), 495-507. https://doi.org/10.1016/j.imed.2026.07.004
Vancouver
Zhang G, An L, Hang C, Wang X, Shao R, Shan Z, et al. Development and validation of an interpretable machine-learning-based model incorporating time-weighted variables for predicting intensive care unit mortality in patients with cardiac arrest: A retrospective study. Intelligent Medicine. 2026;6(5):495-507. doi:10.1016/j.imed.2026.07.004
BibTeX
@article{Zhang2026,
author = {Zhang, Guyu and An, Le and Hang, Chenchen and Wang, Xingsheng and Shao, Rui and Shan, Zhenyu and Tang, Ziren},
title = {Development and validation of an interpretable machine-learning-based model incorporating time-weighted variables for predicting intensive care unit mortality in patients with cardiac arrest: A retrospective study},
journal = {Intelligent Medicine},
year = {2026},
volume = {6},
number = {5},
pages = {495--507},
doi = {10.1016/j.imed.2026.07.004}
}
EUVIMED