Heart Attack Prediction using Machine Learning

In the recent years, the coronary artery disease (CAD) becomes leading cause of mortality worldwide both in high-income nations and in poor countries to a rising extent. Studies of human genetics can provide useful information for the development of such enhanced techniques by enhancing our ability to identify those who are at a higher risk for CAD. This work explores artificial intelligence technologies that analyze raw clinical data for the study and assessment of heart disease severity. Further utilizes machine learning algorithms to predict various state of CAD in individuals, such as naive bayes (NB), decision tree (DT), and Weighted Associative Rule Mining (WARM). This research study has tested these algorithms on the clinical data obtained from the Cardiology department, which include highlights and distinct cases. The decision tree achieves the highest prediction accuracy of 99.5 percent with the fastest rate of exactness over other algorithms.