Predicting Postoperative Stroke in Elderly SICU Patients: An Interpretable Machine Learning Model Using MIMIC Data

TL;DR

This study developed an interpretable machine learning model using MIMIC data to predict postoperative stroke in elderly SICU patients, achieving high accuracy and identifying key risk factors for early intervention.

Contribution

The paper introduces a novel interpretable ML framework with a two-stage feature selection process for early stroke prediction in elderly SICU patients using large clinical datasets.

Findings

CatBoost model achieved AUROC of 0.8868

Key risk factors include cerebrovascular disease, serum creatinine, and systolic blood pressure

Effective early prediction can improve clinical decision-making

Abstract

Postoperative stroke remains a critical complication in elderly surgical intensive care unit (SICU) patients, contributing to prolonged hospitalization, elevated healthcare costs, and increased mortality. Accurate early risk stratification is essential to enable timely intervention and improve clinical outcomes. We constructed a combined cohort of 19,085 elderly SICU admissions from the MIMIC-III and MIMIC-IV databases and developed an interpretable machine learning (ML) framework to predict in-hospital stroke using clinical data from the first 24 hours of Intensive Care Unit (ICU) stay. The preprocessing pipeline included removal of high-missingness features, iterative Singular Value Decomposition (SVD) imputation, z-score normalization, one-hot encoding, and class imbalance correction via the Adaptive Synthetic Sampling (ADASYN) algorithm. A two-stage feature selection process-combining Recursive Feature Elimination with Cross-Validation (RFECV) and SHapley Additive exPlanations (SHAP)-reduced the initial 80 variables to 20 clinically informative predictors. Among eight ML models evaluated, CatBoost achieved the best performance with an AUROC of 0.8868 (95% CI: 0.8802--0.8937). SHAP analysis and ablation studies identified prior cerebrovascular disease, serum creatinine, and systolic blood pressure as the most influential risk factors. Our results highlight the potential of interpretable ML approaches to support early detection of postoperative stroke and inform decision-making in perioperative critical care.