A hybrid GA and PSO optimized approach for heart-disease prediction based on random forest

Abstract Nowadays, heart diseases are significantly contributing to deaths all over the world. Thus, heart-disease prediction has garnered considerable attention in medical domain globally. Accordingly, machine-learning algorithms for early of were developed several studies help physicians design procedures. In this study, a hybrid genetic algorithm (GA) and particle swarm optimization (PSO) optimized approach based on random forest (RF), called GAPSO-RF, is used select optimal features that can increase accuracy prediction. The proposed GAPSO-RF implements multivariate statistical analysis first step most significant initial population. After that, discriminate mutation strategy implemented GA. combines modified GA global search PSO local search. Moreover, achieved concept rehabbing individuals had been refused selection process. performance validated via evaluation metrics, namely, accuracy, specificity, sensitivity, area under receiver operating characteristic (ROC) curve by using two datasets from University California, Cleveland Statlog. experimental results confirm attained high heart-disease-prediction accuracies 95.6% 91.4% Statlog datasets, respectively. Furthermore, outperformed other state-of-the-art methods.