Proactive Prediction of ICU Mortality Using Temporal Infection Trends and Machine Learning Across Multicenter Units
Hospital and Clinical Management · 2025
DOI: 10.58489/2836-2292/013 ↗Kurz gefasst
Fachartikel in der Zeitschrift Hospital and Clinical Management, 2025. Verfasst von Yahya Abdel Tawab Meky.
Abstract (Originalsprache)
Objective
To create a machine learning model that uses clinical and temporal infection data from several units to proactively forecast monthly ICU mortality.
Methods
APACHE II scores, infection occurrences (VAP, CLABSI, CAUTI), ventilatory days > 10, and ICU stay > 10 days were all included in a multicenter dataset of 219 monthly observations from 14 ICUs between May 2024 and October 2025. Gradient Boosting, Random Forest, and Linear Regression models were trained (80/20 split) and assessed using R², RMSE, and MAE.
Results
The best results were obtained by Random Forest (MAE=1.95, RMSE=2.64, R²=0.746). APACHE II score, extended ICU stay, and infection rates were found to be the most significant predictors by feature relevance and SHAP analysis.
Conclusions
The suggested methodology facilitates proactive clinical decision-making and accurately forecasts monthly ICU mortality. Interpretability and operational value are improved by incorporating infection trends. Keywords: ICU, mortality prediction, machine learning, infection rate, APACHE II, Random Forest, SHAP.
Zitieren
APA
Meky, Y. A. T. (2025). Proactive Prediction of ICU Mortality Using Temporal Infection Trends and Machine Learning Across Multicenter Units. Hospital and Clinical Management. https://doi.org/10.58489/2836-2292/013
Vancouver
Meky YAT. Proactive Prediction of ICU Mortality Using Temporal Infection Trends and Machine Learning Across Multicenter Units. Hospital and Clinical Management. 2025. doi:10.58489/2836-2292/013
BibTeX
@article{Meky2025,
author = {Meky, Yahya Abdel Tawab},
title = {Proactive Prediction of ICU Mortality Using Temporal Infection Trends and Machine Learning Across Multicenter Units},
journal = {Hospital and Clinical Management},
year = {2025},
doi = {10.58489/2836-2292/013}
}
EUVIMED