A MACHINE LEARNING APPROACH FOR EARLY RENAL RISK PREDICTION USING IMPROVED SSA AND ANNGO

Abstract

Chronic kidney disease (CKD) is a general term encompassing a number of diverse kidney diseases with increasing frequency and prevalence as well as harmful side effects includes renal failure, cardiovascular disease, and early death. It is sometimes referred to as Chronic Renal Disease a stage of advanced renal function loss. Unfortunately, there is no cure for this ailment, but it is possible to halt its growth and mitigate the harm by diagnosing it early. As a result, it is now of utmost importance to identify such illnesses at an early stage. If the risk factors for chronic kidney disease are identified early on, timely treatment and the proper course of action may be performed. Along with mining tools, machine learning is crucial in overcoming this obstacle. In this research, we used a hybrid model and feature selection technique to construct an hybrid machine learning model to forecast CKD. With an accuracy of 99.87%, the results demonstrated that the proposed classifier performed best in the renal diagnosis method.