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

<span>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 prediction. This study employs three datasets from University California Irvine (UCI) repository: Cleveland, Statlog, and Long Beach, with 14 features each. Recursive feature elimination support vector machine (SVM) utilized identify significant features. Five (gradient algorithm (GB), adaptive (AdaBoost), extreme gradient (XGBoost), cat boost (CatBoost) light (LightGBM)) are integrated into an ensemble model achieve best classification performance. The proposed demonstrates superior accuracy, precision, recall, f-measure, area under curve (AUC) compared individual models, achieving 93.44%, 83.33%, 79.75% accuracies Beach datasets. approach offers accurate efficient method prediction, which crucial clinical decision-making management.</span>