Retracted: Prediction of Heart Disease Using Naive Bayes in Comparison with KNN Based on Accuracy

Abstract

The aim of the study is to predict heart disease by using naive bayes technique and to increase the accuracy in prediction using machine learning classifiers by comparing their performance. Two groups such as Naive Bayes and K-Nearest Neighbour (KNN) are analysed in this research. The algorithms have been implemented and tested over a dataset which consists of 1700 records. Sample size is found to be 540 from clincalc.com with a pretest power of 80%. 20 samples are analysed for statistical analysis. After performing the experiment the mean accuracy is 82.47% by using Naive Bayes algorithm and 79.64% by using k-nearest neighbour algorithm for prediction of heart disease. There is a statistical significant difference in accuracy for two algorithms the p¡O.05 by performing independent samples t-tests. This research is to improve the prediction of heart disease by using machine learning algorithms. Performance and accuracy in prediction of heart disease is carried out for the two algorithms. The comparison results show that Naive Bayes have better performance compared to KNN.