<![CDATA[Diabetes mellitus is a chronic metabolic disease that is increasingly common in Indonesia, estimated to affect more than 10.8 million people in 2020. This disease needs to be recognized early to prevent serious complications that can increase morbidity and mortality. By comparing the two methods, this study was conducted to determine whether one approach shows a better level of accuracy and to develop a classification model based on patient data. The research data was provided by the Anggadita Health Center which includes demographic data, lifestyle, and health assessment results from 1001 patients. One of the research steps is data pre-processing to evaluation. SVM and RF modeling can evaluate models using accuracy, precision, recall, and F1-score metrics. Based on the test results, the Random Forest algorithm showed the best performance with an accuracy of 99%, precision of 99%, recall of 100%, and F1-score of 99%, while SVM got an accuracy of 91%, precision of 0.93%, recall of 0.91%, and F1-score of 0.92%. This shows how well Random Forest separates patients with and without diabetes. This study is expected to be one of the references in obtaining information for making medical decision support systems so that health workers can be faster and more accurate in diagnosing diabetes mellitus.]]>
Copyrights © 2025
