Interpretable Machine Learning Model for Early Prediction of 30-Day Mortality in ICU Patients With Coexisting Hypertension and Atrial Fibrillation: A Retrospective Cohort Study

2025-06-18

AI Summary

Hypertensive ICU patients with atrial fibrillation (AF) face elevated short-term mortality, yet lack validated, subgroup-specific prediction tools. This study is the first to focus exclusively on this high-risk population, developing an interpretable machine learning model to predict 30-day mortality using only clinical data collected within 24 hours of ICU admission. We employed CatBoost as the primary algorithm, benchmarking against LightGBM, XGBoost, and three other ensemble methods; model training incorporated outcome-weighted loss, five-fold cross-validation, multiple imputation, and rigorous feature selection. The final model achieved an AUROC of 0.889 (95% CI: 0.840–0.924), with accuracy and sensitivity both exceeding 0.83. To ensure clinical interpretability, we integrated SHAP, ALE, and DREAM analyses—identifying RASS score, arterial pO₂, cefepime administration, and invasive mechanical ventilation as key, clinically actionable drivers. These findings provide evidence-based targets for early intervention.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Humans and AI: Human-in-the-loop Machine Learning
• 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

Hypertension and atrial fibrillation (AF) often coexist in critically ill patients, significantly increasing mortality rates in the ICU. Early identification of high-risk individuals is crucial for targeted interventions. However, limited research has focused on short-term mortality prediction for this subgroup. This study analyzed 1,301 adult ICU patients with hypertension and AF from the MIMIC-IV database. Data including chart events, laboratory results, procedures, medications, and demographic information from the first 24 hours of ICU admission were extracted. After quality control, missing data imputation, and feature selection, 17 clinically relevant variables were retained. The cohort was split into training (70%) and test (30%) sets, with outcome-weighted training applied to address class imbalance. The CatBoost model, along with five baseline models (LightGBM, XGBoost, logistic regression, Naive Bayes, and neural networks), was evaluated using five-fold cross-validation, with AUROC as the primary performance metric. Model interpretability was assessed using SHAP, ALE, and DREAM analyses. The CatBoost model showed strong performance with an AUROC of 0.889 (95% CI: 0.840-0.924), accuracy of 0.831, and sensitivity of 0.837. Key predictors identified by SHAP and other methods included the Richmond-RAS Scale, pO2, CefePIME, and Invasive Ventilation, demonstrating the model's robustness and clinical applicability. This model shows strong performance and interpretability in early mortality prediction, enabling early intervention and personalized care decisions. Future work will involve multi-center validation and extending the approach to other diseases.

Problem

• Predicts 30-day mortality in ICU patients with hypertension and atrial fibrillation
• Identifies high-risk individuals early for targeted interventions
• Addresses limited research on short-term mortality prediction for this subgroup

Innovation

• CatBoost model for mortality prediction
• SHAP and ALE for interpretability
• Outcome-weighted training for imbalance