Enhancing the Performance of Heart Disease Prediction from Collecting Cleveland Heart Dataset using Bayesian Network

Abstract

Cardiovascular diseases are diseases affecting the general well-being of the heart. It is responsible for many deaths annually. Consequently, this paper focuses on improving the performance of heart disease prediction by collecting Cleveland heart datasets from the University of California Irvine machine learning repository. Different feature subset selection is performed on the dataset and modeled using machine learning models such as logistic regression, K-Nearest neighbor, Naïve Bayes and Bayesian Network. The proposed method achieved an accuracy of 88.53%. Based on the results obtained, we observed feature reduction on the Cleveland dataset could enhance the performance of the Bayesian network.