Performance Analysis of Heart Disease Prediction System using Novel Random Forest Over Naive Bayes Algorithm with an Improved Accuracy Rate

Abstract

Aim: The cardiac is a vital organ in the human body. Life is entirely dependent on the functional workings of the heart. Cardiovascular disease refers to diseases of the cardiac and the blood vessels that supply it. The primary goal of this article is to perform on the exactness of the arrangement of coronary disease expectation utilizing the assistance of AI calculations. We will be comparing the novel Random forest with Naive Bayes to find out which of these can give us the best accuracy. Material and Methods: The study used 1402 samples with Novel Random Forest and Naive Bayes is executed with varying training and testing splits for foreseeing the exactness for coronary illness forecast with the 80% of G-power value and cardiovascular disease information were collected from various website domains using the most recent research and a threshold of 0.05%, a 95% uncertainty range, a mean, and a confidence interval. The accuracy rate of the classifiers is used to evaluate their performance using the heart disease dataset. A statistically insignificant difference exists among the two groups p=0.199; p>0.05. Results and Discussion: The accuracy of predicting heart disease in Novel Random Forest 90.16% and Naive Bayes 85.25% is obtained. Conclusion: Prediction of Heart disease using With enhanced accuracy, the novel Random Forest(RF) the technique appears to be far better to the Naive Bayes(NB).