What question did this study set out to answer?

The study aims to improve 28-day mortality predictions in ICU patients using multi-model fusion techniques.

February 12, 2026Shock0 citations

Multi-Model Fusion for 28-Day Mortality Prediction in ICU Patients: A Comprehensive Retrospective Cohort Study with Subgroup Validation and Clinical Risk Stratification

Key Points

The study aims to improve 28-day mortality predictions in ICU patients using multi-model fusion techniques.
Retrospective cohort study utilizing data from 654 ICU patients
Developed and validated four prediction models: Logistic Regression, Random Forest, Gradient Boosting, and Multi-Model Fusion
Evaluated model performance using AUC-ROC, sensitivity, specificity, and calibration metrics
Conducted subgroup analyses across diverse patient categories
The Multi-Model Fusion model achieved an AUC-ROC of 0.862, outperforming individual models significantly
Equilibrium of sensitivity (84.6%) and specificity (81.0%) was maintained
Results showed strong calibration with a Brier score of 0.140 and consistent performance across subgroups
Identified three mortality risk categories: low-risk (<0.3), moderate-risk (0.3-0.7), and high-risk (>0.7)

Abstract

Background: Accurate prediction of 28-day mortality in intensive care unit (ICU) patients represents a critical challenge in modern critical care medicine, with profound implications for clinical decision-making, resource optimization, and patient-centered care. Traditional severity scoring systems and conventional machine learning approaches have consistently demonstrated limitations in discriminative performance, calibration accuracy, and generalizability across heterogeneous patient populations. Methods: This retrospective cohort study employed comprehensive data from 654 consecutively admitted adult ICU patients at a tertiary academic medical center between August 2022 and August 2024.We developed and rigorously validated four distinct prediction methodologies: Logistic Regression (LR), Random Forest (RF), Gradient Boosting (GB), and an innovative Multi-Model Fusion (MMF) framework incorporating probability averaging from constituent models. Our evaluation framework encompassed exhaustive discrimination metrics (AUC-ROC, sensitivity, specificity, F1-score), sophisticated calibration assessment (Brier score, calibration curves, Hosmer-Lemeshow test), detailed subgroup analyses across clinically relevantpatient strata, and multi-dimensional feature importance evaluation. Results: The Multi-Model Fusion paradigm demonstrated statistically superior performance with an AUC-ROC of 0.862 (95% CI: 0.821-0.903), significantly outperforming all individual models (LR: ΔAUC=0.121, p0.7, 83.3%). Conclusion: The Multi-Model Fusion framework establishes a clinically actionable and methodologically sophisticated paradigm for 28-day mortality prediction in ICU patients, effectively addressing fundamental limitations of conventional approaches through enhanced discriminative performance, exemplary calibration accuracy, and consistent generalizability across diverse patient populations. These compelling findings strongly advocate for its integration intoICU clinical decision support ecosystems to advance prognostic precision and guide personalized therapeutic strategies.

AI से पूछें

Bookmark

View Full Paper