Integrating Fuzzy Logic and Medical Parameters for Reliable Chronic Kidney Disease Risk Prediction

Abstract

This study explores the integration of fuzzy logic with critical medical parameters-Creatinine, Blood Urea Nitrogen (BUN), and Protein in Urine—to enhance the accuracy and reliability of Chronic Kidney Disease (CKD) risk prediction. Traditional diagnostic methods often struggle with the inherent uncertainty and variability in medical data, leading to potential misclassifications. By employing a fuzzy logic-based model, this research systematically incorporates varying levels of the three biomarkers to infer CKD risk levels as Low, Moderate, or High. The fuzzy rule base allows for nuanced decision-making that aligns more closely with clinical observations, providing a more flexible and adaptive approach to risk assessment. This model aims to support healthcare professionals in early diagnosis and improved patient management by offering a transparent, interpretable framework for CKD risk evaluation amidst uncertain data conditions.