A COMPARATIVE STUDY FOR THE PREDICTION OF HEART ATTACK RISK AND ASSOCIATED FACTORS USING MLP AND RBF NEURAL NETWORKS

Abstract— Aim: The aim of this study is to develop a predictive classification model that can identify risk factors for heart attack disease.
 Materials and Methods: In the study, patients with low high probability having were examined. Variable importance was calculated factors. radial basis function multilayer perception neural networks used compare prediction results.
 Results: MLP criteria; Accuracy 0.911, F1 score 0.918, Specificity 0.92, Sensitivity 0.903, while RBF criteria obtained as accuracy 0.797, 0.812, 0.84, 0.765. first three most important may be associated trestbps, oldpeak, chol. 
 Conclusion: According results attack, it said created network has more successful predictions than network. addition, estimating values (obtaining biomarkers cause attack) promising result diagnosis, treatment prognosis Keywords— Heart Attack, machine learning, networks, classification, variable importance.