2025, Vol. 6, Issue 2, Part E

Chronic kidney disease is a progressive medical condition that causes gradual and often irreversible damage to kidney function. Early detection is crucial because most patients remain asymptomatic until the disease reaches advanced stages, at which point treatment options become limited and costly. This study explores the use of machine learning techniques to predict CKD at an early stage using clinical patient data. The raw dataset is preprocessed through data cleaning, handling missing values, and feature encoding to ensure model readiness. Feature selection techniques are applied to identify the most relevant clinical parameters contributing to CKD prediction. Multiple machine learning algorithms, including Decision Tree, Random Forest, Support Vector Machine (SVM), Logistic Regression, and K- Nearest Neighbors (KNN), are trained and evaluated. Their performance is assessed using key metrics such as accuracy, precision, recall, and F1-score. The results highlight the most effective model for reliable CKD detection, demonstrating that machine learning can serve as a valuable decision-support tool for healthcare professionals, enabling timely diagnosis and better treatment planning.