Retrospective Machine Learning Approach for Forecasting In-Hospital Death in ICU Patients After Cardiac Arrest
Preprint
Abstract
Accurate identification of patients at high risk of in-hospital mortality in intensive care units (ICUs) is vital for enhancing clinical decision-making and improving patient care strategies. As traditional statistical models often fall short in modeling nonlinear and multifactorial clinical variables, this study explores a machine learning (ML) approach to overcome these limitations. Our research performed a retrospective study using the MIMIC-IV database, focusing on 2,385 ICU patients who met predefined eligibility criteria. Numerical features were summarized through statistical aggregations (maximum, minimum, mean), while categorical attributes underwent structured encoding. The dataset was split into 70% for training and 30% for validation. We applied a combination of regularization techniques (LASSO, Ridge, ElasticNet) and Random Forest-based importance ranking for feature selection. Multiple supervised ML algorithms, including CatBoost, XGBoost, and Support Vector Machines, were benchmarked using metrics such as AUC-ROC, calibration plots, and decision curve analysis. SHAP values were employed to enhance model explainability. The CatBoost algorithm achieved the most favorable results with AUC scores of 0.904 and 0.868 on the training and test sets. These findings suggest that the proposed model offers a reliable, interpretable, and potentially integrable solution for ICU mortality risk prediction.Keywords
This publication has 41 references indexed in Scilit:
- Comprehensive analysis of machine learning models for prediction of sub-clinical mastitis: Deep Learning and Gradient-Boosted Trees outperform other modelsComputers in Biology and Medicine, 2019
- Growth differentiation factor-15 predicts poor survival after cardiac arrestResuscitation, 2019
- Adult in-hospital cardiac arrest in DenmarkResuscitation, 2019
- Derivation and Validation of the SWAP Score for Very Early Prediction of Neurologic Outcome in Patients With Out-of-Hospital Cardiac ArrestAnnals of Emergency Medicine, 2019
- A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction modelsJournal of Clinical Epidemiology, 2019
- In-Hospital Cardiac ArrestJAMA, 2019
- Periarrest Modified Early Warning Score (MEWS) predicts the outcome of in-hospital cardiac arrestJournal of the Formosan Medical Association, 2016
- Fibroblast growth factor 23 (FGF-23) is an early predictor of mortality in patients with cardiac arrestResuscitation, 2016
- Application of the Gradient Boosted method in randomised clinical trials: Participant variables that contribute to depression treatment efficacy of duloxetine, SSRIs or placeboJournal of Affective Disorders, 2014
- A national analysis of the relationship between hospital factors and post-cardiac arrest mortalityIntensive Care Medicine, 2008