Data Mining to Predict Early Stage Chronic Kidney Disease

Abstract

Chronic Kidney Disease (CKD) is a condition characterized by a gradual loss of kidney function over time. In national and international guidelines, CKD is organized into different degrees of risk stratification using commonly available markers. It is usually asymptomatic in its early stages, and early detection is important to reduce future risks. This study used the CRISP-DM (Cross Industry Standard Process for Data Mining) methodology and the WEKA software to build a system that can classify the chronic condition of kidney disease based on accuracy, sensitivity, specificity and precision. The results obtained were considered satisfactory, achieving the most suitable result of 97.66% of accuracy, 96.13% of sensitivity, 98.78% of specificity and 98.31% of precision with the J48 algorithm.