Prediction of Heart Disease Using Machine Learning Algorithms

Because of modern living habits, heart disease has become a leading cause of death worldwide. Precise diagnosis and early treatment are becoming increasingly important as time goes by. We have used machine learning models and a voting classifier with data from a small sample of people to make predictions about this potentially fatal disease. This data includes the participants' medical histories and demographic information, such as whether or not any members of their immediate families have had heart problems in the past. This research presents a preliminary investigation and analysis by employing a variety of machine learning methods, including KNN, Logistic Nave Bayes, Support Vector Machine, Logistic Regression, and ensemble algorithms ADABoost and XGBoost as voting classifiers. The goal of this study is to determine if a person will develop heart disease. In comparison to other methods, the prediction accuracy of the voting classifier is 98.3%, showing that it performs quite well.