Machine learning is used in several sectors throughout the world. The medical field is not an exception. Heart issues, locomotor abnormalities, and other disorders may be identified with the use of machine learning. If such data could be anticipated in advance, it may provide clinicians with useful clues for personalizing patient diagnosis and treatment. We're aiming to foresee human heart problems using machine learning methods. Classifiers such as decision trees, Naive Bayes, logistic regression, support vector machines, and random forests are compared and contrasted in this research. Given that an ensemble classifier may use different amounts of samples for training and validating, we suggest one that can do hybrid classification using both strong and weak classifiers.