2 A medical intelligent system for diagnosis of chronic kidney disease using adaptive neuro-fuzzy inference system

Abstract

Chronic kidney disease (CKD) occurs when the kidney fails to perform its functions and does not filter or purify the blood accurately. Various factors increase the risks of developing CKD. Hence, to detect this life-threatening disease at the fresh or initial stage, one has to monitor these risk factors regularly before the condition of the individual worsens. In this chapter, the detection of CKD, a deadly and serious disease, is discussed by using an adaptive neuro-fuzzy inference system (ANFIS). The main objective of this study is to enhance the accuracy of the diagnostic systems used for the detection of CKD. The developed ANFIS uses nephron functionality, blood sugar, diastolic blood pressure, systolic blood pressure, age, body mass index and smoking as input variables. The output variable describes the stage of the CKD of a particular patient. The proposed neuro-fuzzy inference system is implemented using the MATLAB software. The developed diagnostic system shows better results, an accuracy of 96% when compared with a fuzzy inference system.