Diagnosis of Chronic Kidney Disease Using ANFIS, FF-ANFIS and GWO-ANFIS Algorithms

Abstract

Chronic kidney disease (CKD) has subtle characteristics in its early stages that may delay identification. Early identification can assist to slow or stop kidney disease from progressing. The current study introduces an expert based on adaptive neuro-fuzzy inference system (ANFIS) to predict the presence or absence of CKD. Furthermore, the suggested system's training parameters were fine-tuned using the firefly (FF) and grey wolf optimization (GWO) algorithm to improve its accuracy. The results show that the GWO optimised ANFIS model is more effective at predicting CKD, with a 95.83% accuracy rate and a root mean square error (RMSE) of 0.2236.