<![CDATA[Chronic Kidney Disease (CKD) is a serious health issue that can lead to death if not detected early. To support early detection, this study applies the eXtreme Gradient Boosting (XGBoost) algorithm to classify patients at risk of CKD. The dataset used is the Chronic Kidney Disease Dataset from Kaggle, consisting of 400 patient records and 26 clinical attributes. Preprocessing involved imputing missing values and converting categorical features into numerical form. The model was evaluated using accuracy, precision, recall, and F1-score metrics. The results show that XGBoost achieved 99% accuracy, with 98% precision and 100% recall, indicating excellent performance in binary classification tasks. This study demonstrates that XGBoost is a reliable algorithm for automatic prediction of chronic kidney disease. Keywords: XGBoost, chronic kidney disease, classification, machine learning]]>
Copyrights © 2025
