<![CDATA[Chronic Kidney Disease, which is often abbreviated as PGK, is a serious disease that is of major concern to society and the medical world. This disease can cause various serious complications if not treated properly and early. Therefore, accurate prediction of CKD is very important to support early intervention that can slow disease progression, prevent further complications, and increase the patient's chances of recovery. This research aims to increase the accuracy of PGK predictions by developing a hybrid model that combines the K-Nearest Neighbors (KNN) algorithm with optimization using the Genetic Algorithm (GA). In this approach, the KNN algorithm is used to build a prediction model, while GA acts as an optimization tool that improves model performance. The effectiveness of the optimized model is evaluated using key metrics such as accuracy, precision, recall, and area under the curve (AUC). The results show a significant increase in performance, with accuracy increasing by 17.75%, precision increasing by 23.84%, and recall increasing by 5.34%. This research makes an important contribution to the development of data mining technology for clinical applications and opens up opportunities for further improvements in the future in increasing the prediction accuracy of chronic diseases such as CKD]]>
Copyrights © 2025
