Heart Attack Prediction Using Machine Learning Technique

Abstract

The subject of AI known as machine learning has been at the forefront of several recent statistical and technological advances. It’s a branch of AI. Improved health outcomes can be achieved with the help of machine learning since it can increase patient participation in the treatment process. Machine learning methods can improve the diagnosis accuracy at every level by identifying the most likely reason for all similar patients' test findings. People over the age of 60 have a higher risk of experiencing a heart attack, and the prevalence of heart attacks increases with age. In order to foretell the onset of a heart attack, researchers are using a number of machine learning techniques. The goal of this study is to describe in depth the methods we use to predict cardiovascular disease, including Decision Tree, K-nearest neighbors, Logistic Regression, XGBoost, Support Vector Machine, and Random Forest. Predictive data mining techniques have been tested on the same dataset with varying degrees of success, and Random Forest methods have been shown to yield the highest accuracy of 87%.