FRBF: A Fuzzy Rule Based Framework for Heart Disease Diagnosis

Abstract

Heart disease is also known as cardiovascular disease, and it is one of the most dangerous and deadly diseases all over the globe. Cardiovascular disease is considered a significant illness in old and middle age. Still, recent trends have shown that cardiovascular disease is also a deadly disease in the young age group due to irregular habits. However, Angiography is one of the ways to diagnose heart disease, but it is costly and has significant side effects. This research paper aims to design a fuzzy rule-based framework to analyze heart disease risk levels. Our proposed framework used a Mamdani interface system and utilized the UCI machine repository dataset for heart disease diagnosis. In this proposed study, we have used ten input attributes and one output attribute with 554 rules. Besides, a comparative table is presented, where the proposed methodology is better than other methodologies. According to the suggested methodology results, the performance is highly successful, and it is a promising tool for identifying a heart disease patient at an early stage. We have achieved accuracy, sensitivity rates of 95.2% and 87.04%, respectively, on the UCI dataset.