A Comparative Analysis of Various Data Mining Techniques to Predict Heart Disease

Abstract

Identifying cardiovascular diseases (CVD) in people at risk is a keystone for preventive cardiology. The risk forecasting tools recently suggested by medicinal plans naturally depend on the restricted numeral of predictions with sub-optimal interpretation beyond all groups of patients. Information-driven approaches depend on Machine Learning to enhance the interpretation of prediction by determining new techniques. This research helps recognize the current procedures included in predicting heart disease by classification in data mining. A review of related DM procedures that are included in heart disease prediction gives an acceptable prediction model. The main inspiration of the paper is to progress an efficient, intelligent medicinal decision system depending upon data mining techniques.