Two-level boosting classifiers ensemble based on feature selection for heart disease prediction

Abstract

Heart disease is a prevalent global health concern, necessitating early detection to save lives. Machine learning has revolutionized medical research, prompting the investigation of boosting algorithms for heart disease prediction. This study employs three heart disease datasets from the University of California Irvine (UCI) repository: Cleveland, Statlog, and Long Beach, with 14 features each. Recursive feature elimination with a support vector machine (SVM) is utilized to identify significant features. Five boosting algorithms (gradient boosting algorithm (GB), adaptive boosting algorithms (AdaBoost), extreme gradient boosting algorithm (XGBoost), cat boost algorithm (CatBoost) and light gradient boosting algorithms (LightGBM)) are integrated into an ensemble model to achieve the best classification performance. The proposed model demonstrates superior accuracy, precision, recall, f-measure, and area under the curve (AUC) compared to individual boosting models, achieving 93.44%, 83.33%, and 79.75% accuracies for Cleveland, Statlog, and Long Beach datasets. This approach offers an accurate and efficient method for heart disease prediction, which is crucial for clinical decision-making and disease management.