Heart disease prediction using naive bayes, decision tree warm weighted associated rule mining

Abstract

Coronary artery supply path Atherosclerosis in coronary corridors causes coronary disease (CAD), which leads to heart failure and cardiovascular failure. Angiography is an expensive, time-consuming, and highly specialised invasive treatment used to identify CAD. As a result, analysts are encouraged to use optional approaches such as AI computations that might use non-intrusive clinical data to determine the severity of a cardiac ailment. Order of Directed learning calculations like guileless bayes, choice tree, WARM weighted related principle mining is utilised to show creepy events. We tested our technique on clinical data acquired from the Cardiology department, which included highlights and events. Choice tree delivers the most elevated pace of exactness accomplishes most elevated forecast precision of 99.5%. This approach was also tested on a seat-checked heart coronary disease informational index. Similarly, MLR outsmarts other processes in similar case. The proposed hybridised model focuses on increasing the accuracy of grouping computations from 8.3% to 11.4 percent for the coronary illness informational index. As a result, the suggested approach provides a potential strategy for identifying CAD sufferers who have improved their condition classification accuracy.