Open Access

ARTICLE

A Meta-Learning Model for Mortality Prediction in Patients with Chronic Cardiovascular Disease

Sam Rahimzadeh Holagh¹, Bugao Xu^1,2,*

1 Department of Information Science, University of North Texas, Denton, TX 76201, USA
2 Department of Merchandising and Digital Retailing, University of North Texas, Denton, TX 76201, USA

* Corresponding Author: Bugao Xu. Email:

Computer Modeling in Engineering & Sciences 2025, 145(2), 2383-2399. https://doi.org/10.32604/cmes.2025.072259

Received 22 August 2025; Accepted 22 October 2025; Issue published 26 November 2025

Abstract

Cardiovascular diseases (CVD) remain a leading cause of mortality worldwide, highlighting the need for precise risk assessment tools to support clinical decision-making. This study introduces a meta-learning model for predicting mortality risk in patients with CVD, classifying them into high-risk and low-risk groups. Data were collected from 868 patients at Tabriz Heart Hospital (THH) in Iran, along with two open-access datasets—the Cleveland Heart Disease (CHD) and Faisalabad Institute of Cardiology (FIC) datasets. Data preprocessing involved class balancing via the Synthetic Minority Over-Sampling Technique (SMOTE). Each dataset was then split into training and test sets, and 5-fold cross-validation was employed to validate generalizability. Several machine-learning algorithms were stacked as base classifiers to generate meta-features, which were then input to a meta-learner combining their predictive strengths through soft voting. An ablation experiment was performed to identify the optimal configuration with two base classifiers—Random Forest (RF) and Support Vector Machine (SVM)—and two boosting classifiers—AdaBoost (ADB) and XGBoost (XGB). The model achieved 88% accuracy, 91% AUC, and 79.1% sensitivity on the THH dataset; 82.77% accuracy, 89.37% AUC, and 93.72% sensitivity on the CHD dataset; and 81.8% accuracy, 82.8% AUC and 78.8% sensitivity the FIC dataset, demonstrating the model’s generalizability across diverse datasets. To further enhance interpretability, Shapley Additive Explanations (SHAP) were applied to quantify each attribute’s contribution to predicted CVD risk, providing both global and local insights to help clinicians identify key risk factors and guide personalized care.

---

Keywords

---