Combining ECG Foundation Model and XGBoost to Predict In-Hospital Malignant Ventricular Arrhythmias in AMI Patients

2025-10-20

AI Summary

To address the clinical challenge of balancing predictive accuracy and interpretability in early in-hospital prediction of malignant ventricular tachyarrhythmias (VT/VF) among acute myocardial infarction (AMI) patients, this study proposes a hybrid framework integrating an electrocardiogram (ECG) foundation model with interpretable machine learning. Specifically, the ECGFounder model is leveraged to automatically extract 150-dimensional diagnostic probability features from raw ECG signals; SHAP (Shapley Additive Explanations) is then applied for clinically guided feature selection and attribution-based interpretation; finally, XGBoost serves as the downstream classifier. The resulting model achieves an AUC of 0.801—significantly outperforming KNN, RNN, and 1D-CNN baselines. SHAP-based feature attribution reveals patterns strongly aligned with established cardiovascular pathophysiology, empirically validating the efficacy and clinical credibility of the “foundation model + interpretable ML” paradigm for cardiovascular risk prediction.

Technology Category

• Machine Learning: Transparent, Interpretable, Explainable ML
• Computer Vision: Interpretability, Explainability, and Transparency
• Humans and AI: Explainable AI (XAI) for Human Understanding

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Malignant ventricular arrhythmias (VT/VF) following acute myocardial infarction (AMI) are a major cause of in-hospital death, yet early identification remains a clinical challenge. While traditional risk scores have limited performance, end-to-end deep learning models often lack the interpretability needed for clinical trust. This study aimed to develop a hybrid predictive framework that integrates a large-scale electrocardiogram (ECG) foundation model (ECGFounder) with an interpretable XGBoost classifier to improve both accuracy and interpretability. We analyzed 6,634 ECG recordings from AMI patients, among whom 175 experienced in-hospital VT/VF. The ECGFounder model was used to extract 150-dimensional diagnostic probability features , which were then refined through feature selection to train the XGBoost classifier. Model performance was evaluated using AUC and F1-score , and the SHAP method was used for interpretability. The ECGFounder + XGBoost hybrid model achieved an AUC of 0.801 , outperforming KNN (AUC 0.677), RNN (AUC 0.676), and an end-to-end 1D-CNN (AUC 0.720). SHAP analysis revealed that model-identified key features, such as "premature ventricular complexes" (risk predictor) and "normal sinus rhythm" (protective factor), were highly consistent with clinical knowledge. We conclude that this hybrid framework provides a novel paradigm for VT/VF risk prediction by validating the use of foundation model outputs as effective, automated feature engineering for building trustworthy, explainable AI-based clinical decision support systems.

Problem

• Predicting malignant ventricular arrhythmias in AMI patients during hospitalization
• Improving prediction accuracy while maintaining clinical interpretability
• Developing hybrid AI framework combining ECG foundation model with XGBoost

Innovation

• Combining ECG foundation model with XGBoost classifier
• Extracting diagnostic features through automated ECG analysis
• Using SHAP method for clinical interpretability validation