Fuzzy Logic based Expert System for Early Predicting of Chronic Kidney Disease

Abstract

Chronic kidney disease (CKD) is a dangerous illness defined as the presence of kidney damage in which the kidney cannot filter blood the way they should. the damage to the human kidneys occurs gradually over a long period. There are five stages in the development of CKD, in the late stage the patient needs a kidney transplant or dialysis treatment to remain alive. Early diagnosis of kidney disease (stages 1 to 3) can slow its progression and minimize its complications in patients. Numerous methods and models have been developed to diagnose CKD in its early stages. In this paper, we employ fuzzy logic theory to develop an expert system to diagnose and predict CKD. The most difficult task in designing a fuzzy logic-based system is to find a set of fuzzy rules and construct membership functions. Therefore, in this study we use Fuzzy C-means clustering (FCM) method to automatically cluster the training data and generate fuzzy rules along with membership functions. The system was implemented on MATLAB software. The experimental result showed that the designed system attains a higher outcome than the existing methods, achieving a remarkable accuracy of 100%.