<![CDATA[Diabetes mellitus is a chronic metabolic disease characterized by high blood glucose levels and has the potential to cause various complications if not detected early. The use of machine learning technology is increasingly developing in the health sector because it can help the process of analyzing and classifying diseases based on patient data. This study aims to apply the K-Nearest Neighbor (KNN) algorithm to classify diabetes using the Pima Indians Diabetes Dataset. The dataset used consists of 768 patient data with 8 predictor attributes and 1 target attribute. The research stages include data cleaning and improvement through preprocessing, data normalization using the Min-Max Scaling method, dividing the dataset into training data and testing data with a ratio of 80:20, and the application of the KNN algorithm with a K value of 5. Model performance evaluation was carried out using a Confusion Matrix which produces Accuracy, Precision, Recall, and F1-Score values. Based on the test results, the model obtained Accuracy of 74.68%, Precision of 66.00%, Recall of 60.00%, and F1-Score of 62.86%. These results demonstrate that the KNN algorithm is capable of classifying diabetes data with fairly good performance based on available health attributes. This research is expected to serve as a reference in the development of machine learning-based decision support systems to aid in the identification of diabetes.]]>
Copyrights © 2026
