Skip to content
Open access

Explainable heterogeneous ensemble learning with hybrid feature selection for heart disease prediction

2026 · Journal of Computational Mathematics, Intelligent and Secure Systems · pp. 115-131 · 0 citations

Abstract

The paper introduces an ensemble learning framework for predicting heart disease with a combination of the pre-processing, hybrid feature selection, class-imbalance management, hyper-parameters optimization, ensemble learning, and Explainable Artificial Intelligence (XAI). For feature selection, the presented framework makes use of Mutual Information and Recursive Feature Elimination, while SMOTE is used for improving the representation of the minority-class. Four tree-based machine learning models are optimized and combined in a weighted performance-based soft-voting ensemble. SHAP’s (SHapley Additive exPlanations) are used to interpret the global importance of selected features as well as the results produced by each model. The experiments are carried out using the Cleveland Heart Disease dataset with the repeated stratified five-fold cross-validation with three repetitions. As a result chest pain, thalassemia, number of major vessels, ST depression, exercise-induced angina, maximum heart rate, ST-segment slope and cholesterol have been identified as the most important features for the prediction of the heart disease.

Read PDF

Similar papers

Conference Open access Sep 2026

Machine Learning Models with Hybrid Ensemble Strategies Using Feature Engineering of Heart Disease Prediction

Cardiovascular disease (CVD) is the number one cause of death worldwide, leading to millions of deaths each year and placing heavy pressure on health systems. Early diagnosis and management of heart disease is critical to optimize patient care and prevent adverse results. Many machine learning algorithms have been used...

V. Lakkamraju, S. Allada, G. Kumar et al. · 0 citations
Sep 2026

Ensemble and Explainable AI-Based Framework for Early Prediction of Heart Disease

The proposed hybrid and explainable machine learning architecture demonstrates substantial predictive accuracy, robustness, and interpretability for the early detection of heart disease.

Sudipta Bhattacharya, Bingshati Mondal, Nabanita Das et al. · 0 citations
Open access Oct 2026

ENSEMBLE LEARNING FOR HEART DISEASE PREDICTION: A NOVEL APPROACH USING ACCURACY-BASED WEIGHTED AGING CLASSIFIER ENSEMBLE

The early detection of the risk for heart disease is crucial for the prevention of cardiovascular diseases which is still the leading cause of death globally. This paper introduces an ICIT2F mean partitioning-based CART model for heart disease classification if integrated with four others models. In this method, the en...

Muhammad Adnan, Usman Humayun, Attra Ali et al. · 0 citations
Open access Oct 2026

Comparative Analysis of Ensemble Learning Models for Cardiovascular Disease Using Explainable Artificial Intelligence

Cardiovascular disease is one of the leading causes of death worldwide, making early risk detection essential to support clinical decision-making. Although machine learning models have been widely applied to cardiovascular disease prediction, challenges remain in achieving consistent performance improvements through en...

Syifa Alfariani, Fathoni Fathoni · 0 citations
Open access Sep 2026

Group-Aware and Explainable Machine Learning Framework for Heart Disease Prediction Using Optimized CatBoost

Accurate and reliable heart disease prediction can support early risk assessment and improve clinical decision-making. However, repeated or duplicate observations in widely used heart disease datasets can introduce data leakage and lead to overly optimistic performance estimates. This study proposes a duplicate-aware a...

Romaan Khan, Tufail Khan, Muhammad Tahir et al. · 0 citations
Conference Open access Sep 2026

Early Diabetes Prediction using Explainable Ensemble Learning and Boruta–SHAP

Diabetes is a long-term metabolic disease that has to be diagnosed as soon as possible to lower the risk of serious health issues. Although machine learning has proven to be a successful method for early diabetes prediction, issues such class imbalance, irrelevant information, and limited model interpretability frequen...

P. Kumar, Karunakumar Valicharla · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.