FRBF: A Fuzzy Rule Based Framework for Heart Disease Diagnosis

Abstract

Heart disease is also known as cardiovascular disease. It is one of the most dangerousand deadly disease in all over the globe. Cardiovascular disease was deemed as amajor illness in old and middle age, but recent trends shown that now cardiovasculardisease is also a deadly disease in young age group due to irregular habit. However,Angiography is one of the way to diagnose heart disease, but it is very expensive andalso has major side effect. The aim of this research paper is to design a fuzzy rulebased framework to diagnosis of the risk level of the heart disease. Our proposedframework used a Mamdani interface system and used UCI machine repositorydataset for heart disease diagnosis. In this proposed study, we have used 10 Inputattribute and one output attribute with 554 rules. Besides, a comparative table is alsopresented, where proposed methodology is better than other methodology. Accordingto the proposed methodology results, that the performance is highly successful and itis a promising tool for identification of a heart disease patient at an early stage. Wehave achieved accuracy, sensitivity rates of 95.2% and 87.04 respectively, on the UCIdataset.