Analyzing Machine Learning Classifiers for the Diagnosis of Heart Disease

Abstract

INTRODUCTION: Preventable deaths from cardiovascular diseases outnumber all others combined. Detecting it at an early stage is crucial. Human lives will be saved as a result. OBJECTIVES: Improved cardiac disease prediction using machine learning classifiers is the focus of this article. METHODS: We have used many different classifiers, such as the support vector machine, naive bayes, random forest, and k-nearest neighbours, to achieve this goal, even though we can’t predict high accuracy in this classifier. So, we have proposed Hyper parameter adjustment was applied to the classifiers, which increased their precision. It was possible to compare the classifiers. RESULTS: In comparison to other machine learning classifiers, Logistic Regression achieves higher prediction accuracy, at 95.5%. CONCLUSION: To help people find the nearest cardiac care facilities, Google Maps has been integrated into a responsive web application that has been built for forecasting heart illness.