Description

Heart disease is one of the foremost critical human diseases within the world and affects human life very badly. In heart conditions, the guts are unable to push the specified amount of blood to other parts of the body. Accurate and on-time diagnosis of heart condition is vital for coronary failure prevention and treatment. The diagnosis of heart condition through traditional medical records has been considered as not reliable in many aspects. To classify healthy people and other people with heart conditions, noninvasive-based methods like machine learning are reliable and efficient. Within the proposed study, we developed a machine-learning-based diagnosis system for heart condition prediction by using a heart condition dataset. We used seven popular machine learning algorithms, three feature selection algorithms, the cross-validation method, and 7 classifiers performance evaluation metrics like classification accuracy, specificity, sensitivity, Matthews' coefficient of correlation, and execution time.