Comparison of Decision Trees, Naïve Bayes and Random Forest in Detecting Heart Disease

Abstract

The leading cause of human death is heart disease (HD) worldwide which generally occurs when the heart is unable to push enough fresh, oxidized blood to the rest of the body. This disease makes it more difficult for the heart muscle to pump blood efficiently and causes chest pain, chest pressure, shortness of breath, pain in the neck and jaw. The aim of this research is to compare and obtain the best accuracy results from the three methods used, namely Random Forest, Extra Trees Classifier and Naïve Bayes. The results of this research prove that the Extra Trees Classifier method with an accuracy of 86.93% has higher results compared to the Naïve Bayes method with an accuracy of 84.21%, and the Random Forest Classifier method with an accuracy of 84.21%. Meanwhile, the AUC results obtained by the Extra Trees Classifier method are higher than other methods with an AUC of 93.81%.