Interpretable Heart Disease Prediction via a Weighted Ensemble Model: A Large-Scale Study with SHAP and Surrogate Decision Trees

TL;DR

This study develops an interpretable, high-performing ensemble model combining tree-based methods and CNN for heart disease prediction, utilizing explainability tools like SHAP and surrogate trees to enhance clinical transparency.

Contribution

Introduces a weighted ensemble model integrating multiple architectures with explainability techniques for improved, interpretable heart disease risk prediction on large-scale data.

Findings

Achieved a Test AUC of 0.8371, significantly better than individual models.

High recall of 80% suitable for screening applications.

Model provides transparency through SHAP and surrogate decision trees.

Abstract

Cardiovascular disease (CVD) remains a critical global health concern, demanding reliable and interpretable predictive models for early risk assessment. This study presents a large-scale analysis using the Heart Disease Health Indicators Dataset, developing a strategically weighted ensemble model that combines tree-based methods (LightGBM, XGBoost) with a Convolutional Neural Network (CNN) to predict CVD risk. The model was trained on a preprocessed dataset of 229,781 patients where the inherent class imbalance was managed through strategic weighting and feature engineering enhanced the original 22 features to 25. The final ensemble achieves a statistically significant improvement over the best individual model, with a Test AUC of 0.8371 (p=0.003) and is particularly suited for screening with a high recall of 80.0%. To provide transparency and clinical interpretability, surrogate decision trees and SHapley Additive exPlanations (SHAP) are used. The proposed model delivers a combination of robust predictive performance and clinical transparency by blending diverse learning architectures and incorporating explainability through SHAP and surrogate decision trees, making it a strong candidate for real-world deployment in public health screening.