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

2025-06-02

AI Summary

This study addresses the challenge of predicting postoperative stroke risk in elderly surgical ICU patients. We constructed a large-scale cohort of 19,085 patients from MIMIC-III/IV and developed an interpretable machine learning model using clinical data collected within the first 24 hours prior to ICU admission. Methodologically, we introduced a novel two-stage interpretable feature selection framework combining recursive feature elimination with cross-validation (RFECV) and SHAP analysis, identifying cerebrovascular disease history, serum creatinine, and systolic blood pressure as the top three modifiable risk factors. The model integrates CatBoost, iterative SVD-based imputation, ADASYN oversampling, and z-score normalization. It achieves an AUROC of 0.8868 (95% CI: 0.8802–0.8937), significantly outperforming conventional clinical scoring systems. The approach delivers both high predictive accuracy and clinical interpretability, enabling early risk stratification and informing targeted, evidence-based interventions.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Predicting postoperative stroke risk in elderly SICU patients
• Developing interpretable ML model using early ICU data
• Identifying key clinical predictors for stroke prevention

Innovation

• Interpretable ML model predicts postoperative stroke
• SVD imputation and ADASYN handle data issues
• CatBoost with SHAP selects key clinical features