Predictive Modeling of Chronic Kidney Disease Using Machine Learning Techniques

Abstract

Chronic Kidney Disease (CKD) represents a major global health burden, often progressing silently until advanced stages. Timely identification is critical for implementing therapeutic strategies that delay disease progression. This study proposes a machine learning for early CKD prediction using clinical and demographic data from the UCI repository. The methodology incorporates data preprocessing and applies three supervised learning algorithms: Random Forest, Decision Tree, and Support Vector Classifier. The models are evaluated using standard performance metrics including accuracy, sensitivity, specificity, and F1-score. Random Forest achieved the highest performance across all metrics, highlighting its potential for integration into clinical decision support tools. The study shows the importance of model interpretability and reliability in healthcare applications.