<![CDATA[Chronic Kidney Disease (CKD) is a significant global health issue that requires early detection to prevent serious complications. In the field of healthcare, the Naïve Bayes algorithm has shown potential as an effective method for classifying medical data, including CKD, due to its simplicity yet accuracy in handling data with independent variables. This study aims to conduct a literature review on the application of the Naïve Bayes algorithm in CKD classification, focusing on the accuracy, efficiency, and reliability of the resulting models. The research analyzes various previous studies, including data preprocessing techniques, important features used, and performance model evaluations based on parameters such as accuracy, precision, and recall. The review findings indicate that the Naïve Bayes algorithm offers competitive accuracy for classifying CKD compared to other methods, especially on datasets with a limited number of features. The conclusion of this review highlights the importance of optimal data management and the selection of relevant features to improve the performance of the Naïve Bayes algorithm. This study is expected to provide guidance for future researchers in developing early detection systems for CKD based on machine learning.]]>
Copyrights © 2024
