A comparison of three discrete methods for classification of heart disease data

Abstract

The classification of heart disease patients is of great importance in cardiovascular disease diagnosis. Numerous data mining techniques have been used so far by the researchers to aid health care professionals in the diagnosis of heart disease. For this task, many algorithms have been proposed in the previous few years. In this paper, we have studied different supervised machine learning techniques for classification of heart disease data and have performed a procedural comparison of these. We have used the C4.5 decision tree classifier, a naïve Bayes classifier, and a Support Vector Machine (SVM) classifier over a large set of heart disease data. The data used in this study is the Cleveland Clinic Foundation Heart Disease Data Set available at UCI Machine Learning Repository. We have found that SVM outperformed both naïve Bayes and C4.5 classifier, giving the best accuracy rate of correctly classifying highest number of instances. We have also found naïve Bayes classifier achieved a competitive performance though the assumption of normality of the data is strongly violated.

Bangladesh J. Sci. Ind. Res. 50(4), 293-296, 2015