<![CDATA[Chronic Kidney Disease (CKD) is a global health problem with morbidity rates that continue to increase from year to year. The main challenge in the medical management of CKD is delayed diagnosis due to early symptoms that are often unnoticed by patients, thereby requiring rapid, objective, and accurate detection methods. This study aims to analyze and compare the performance of two popular classification algorithms, K-Nearest Neighbor (kNN) and Random Forest, in classifying chronic kidney disease status. Experiments were conducted using Orange Data Mining software by utilizing a patient clinical medical record dataset. The model evaluation was rigorously tested using the 10-Fold Cross Validation method to ensure the validity of the results. The main contribution of this study is to present an in-depth comparative analysis regarding the evaluation metrics of ensemble trees compared to distance-based approaches to minimize the risk of missed diagnosis in clinical decisions. The results showed that the Random Forest algorithm produced the best and superior performance with an accuracy rate (Accuracy) reaching 99.0%, a Precision value of 99.3%, and an AUC value of 0.999. Conversely, the K-Nearest Neighbor algorithm obtained a lower accuracy rate of 96.0% with an AUC of 0.994. These findings indicate that the ensemble tree approach is more adaptive in handling clinical data characteristics, and has great potential to be integrated as a clinical decision support system for medical personnel in hospitals.]]>
Copyrights © 2026
