Machine learning is utilized in numerous fields worldwide. The medical services industry is no rejection. Predicting the presence or absence of heart diseases, locomotor disorders, and other diseases can all benefit from machine learning. If this information is predicted well in advance, it can give doctors important clues that they can use to adjust their diagnosis and treatment for each patient. Using machine learning algorithms, we try to predict people's risk of developing heart disease. By combining both strong and weak classifiers, our ensemble classifier performs hybrid classification. We analyze both existing classifiers and proposed classifiers like Ada-boost and XG-boost, which can have multiple samples for training and validating the data to provide better accuracy and predictive analysis. This project's comparative analysis focuses on classifiers like decision trees, naive bayes, logistic regression, and random forests.

Heart prediction, Decision tree, logistic regression, Naive Bayes, Random Forest, and KNN.