A Comparative Analysis of Supervised Classification Algorithms and Missing Data Handling for Enhancing Chronic Kidney Disease Prediction

Abstract

Chronic kidney disease (CKD), which is becoming a more significant public health concern, is characterized by a gradual but concerning increase in morbidity and death, particularly in its early, asymptomatic stages. Risk factors for chronic kidney disease (CKD), including genetic predisposition, obesity, diabetes, and hypertension, affect the illness's prevalence. When there are no outward signs of an illness, it is challenging to diagnose and treat it in its early stages. To tackle this pressing issue, our research does a comprehensive investigation through a comparative comparison of supervised classification techniques. In particular, we examine the prediction performance of CKD using the Random Forest, Decision Tree, and Support Vector Machine (SVM) techniques. We also look into a number of approaches to handling missing data. Our research presents a thorough evaluation of these algorithms' performance under different data cleaning methods, pointing out both their benefits and drawbacks. Ultimately, our research aims to clarify the early detection and treatment of chronic kidney disease (CKD) and pave the way for larger-scale public health initiatives to tackle this quickly escalating health emergency.