Leveraging Machine Learning Algorithms for Prediction Chronic Kidney Disease: A Comparative Analysis

Chronic kidney disease (CKD) is a progressive condition characterized by the gradual decline of kidney function, often caused by diabetes, hypertension, or cardiovascular issues. It develops silently, with symptoms emerging slowly, leading to significant health complications. The increasing global prevalence of CKD highlights the urgent need for early detection and effective treatment strategies. In this study, we leverage machine learning techniques to improve the identification and prediction of CKD. Four models. AdaBoostClassifier, XGBClassifier, LGBMClassifier, and RandomForestClassifie. were evaluated for their performance. Among these, the XGBClassifier achieved the highest average training accuracy of 95.78%. Evaluation metrics such as the confusion matrix, ROC curve, and classification report (including F1-score, precision, and recall) were employed to assess the models comprehensively. The study demonstrates the potential of machine learning in enhancing CKD diagnosis by leveraging advanced algorithms to analyze patient data effectively.