Optimized Ensemble model for Heart Disease Prediction using Machine Learning

Abstract

Heart disease is a cluster of conditions that affect the heart and blood vessels. Cardiovascular disease (heart disease) includes many factors such as blood pressure, cholesterol, blood sugar, obesity, and many more that causes it. This research aims to predict the risk of heart attacks or disease. This dataset is collected from the open-source platform Kaggle Machine Learning Repository. To accomplish this prediction, an optimized ensemble model is proposed using various typical modern machine learning algorithms that are Bagging, RandomForest, Kstar, and RandomForest. A remarkable Accuracy of 96% is provided by an optimized ensemble model that is adequate to predict the risk of heart disease. The findings of the study can be used by healthcare providers to develop customized treatment plans and preventative measures that will reduce the risk of heart disease and improve patient outcomes.