Heart Plaque Detection with Improved Accuracy using Naive Bayes and comparing with Least Squares Support Vector Machine

Abstract

Aim: The main aim of this research is to detect heart plaque using the Naive Bayes algorithm with improved accuracy and comparing it with Least Squares Support Vector Machine. Materials and Methods: Naive Bayes algorithm and Least squares Support Vector Machine algorithms are two groups compared in this study. In the Kaggle dataset on Heart Plaque Disease, there were a total of 20 samples. Clincalc is used to calculate sample G power of 0.08 with 95% confidence interval. The training dataset (n = 489 (70 %)) and the test dataset (n = 277 (30 %)) are divided into two groups. Result: The accuracy of the Naive Bayes algorithm and the Least Squares Support Vector Machine algorithm is assessed. The Naive Bayes method was 78% accurate, whereas the Least Squares Support Vector Machine method was only 67.3% correct.Conclusion: In this work, the Naive Bayes algorithm outperformed the Least Squares Support Vector Machine algorithm in detecting heart plaque disease in the dataset under consideration. Keywords Heart Plaque disease, Novel intensity feature, Naive Bayes algorithm, Least Squares Support Vector Machine, Prediction, Machine learning.