Machine Learning-Based Prediction of ICU Readmissions in Intracerebral Hemorrhage Patients: Insights from the MIMIC Databases

TL;DR

Predicting ICU readmission for intracerebral hemorrhage (ICH) patients is clinically important for patient care and resource management. The study leverages MIMIC-III and MIMIC-IV data to train an Artificial Neural Network with ADASYN to address class imbalance, employing Recursive Feature Elimination and expert input to select 12 predictors, and comparing performance against XGBoost and Random Forest baselines. The ANN achieves the best performance (AUROC $0.899$, 95% CI: $0.860$–$0.911$) with high sensitivity ($0.893$) and interpretable SHAP explanations highlighting age, Chloride, MCHC, and Monocytes as key drivers. These results support clinical deployment for risk stratification and resource planning, though external validation on diverse datasets is needed to confirm generalizability.

Abstract

Intracerebral hemorrhage (ICH) is a life-risking condition characterized by bleeding within the brain parenchyma. ICU readmission in ICH patients is a critical outcome, reflecting both clinical severity and resource utilization. Accurate prediction of ICU readmission risk is crucial for guiding clinical decision-making and optimizing healthcare resources. This study utilized the Medical Information Mart for Intensive Care (MIMIC-III and MIMIC-IV) databases, which contain comprehensive clinical and demographic data on ICU patients. Patients with ICH were identified from both databases. Various clinical, laboratory, and demographic features were extracted for analysis based on both overview literature and experts' opinions. Preprocessing methods like imputing and sampling were applied to improve the performance of our models. Machine learning techniques, such as Artificial Neural Network (ANN), XGBoost, and Random Forest, were employed to develop predictive models for ICU readmission risk. Model performance was evaluated using metrics such as AUROC, accuracy, sensitivity, and specificity. The developed models demonstrated robust predictive accuracy for ICU readmission in ICH patients, with key predictors including demographic information, clinical parameters, and laboratory measurements. Our study provides a predictive framework for ICU readmission risk in ICH patients, which can aid in clinical decision-making and improve resource allocation in intensive care settings.

Figures (5)

• Figure 1: Criterion of study population extraction
• Figure 2: Variance Inflation Factor of selected features.
• Figure 3: AUROC-curves for test set of our three Machine Learning Models
• Figure 4: Feature importance ranking based on mean absolute SHAP values
• Figure 5: SHAP summary plot showing the distribution of SHAP values for each feature. Each dot represents an individual prediction, colored by the feature value (blue: low, red: high).