Review on fuzzy expert system and data mining techniques for the diagnosis of coronary artery disease

Abstract

According to World Health Organization (WHO), Coronary Artery Disease (CAD) has become the leading cause of death in many countries, especially in Asia. In Indonesia itself, CAD becomes the second rank for the cause of death because 9.89% of the total number of deaths is caused by CAD. This paper focused on reviewing possible algorithm types of data mining, fuzzy, and combination between data mining and fuzzy applied for dataset processing and classification to identify patients suspected of having CAD and optimized in minimal time with high accuracy. The choice of data to design a detection system also varied. Standart datasets with relevant features are used to facilitate detection of abnormalities with the maximum detection rate. The use of data mining techniques produced the highest accuracy of 99%, they were with J48 algorithm, Naive Bayes, REPTREE, CART, and Bayes Net. The use of fuzzy produced accuracy of 94% that was by methods of mamdani inference system and fuzzy membership function of triangle and trapezoid. The use of data mining and fuzzy produced 94.92% with decision tree algorithms, fuzzy, and ICA.