<![CDATA[Hyperglycemia, or elevated blood glucose levels, is a primary indicator of diabetes mellitus, a chronic metabolic disorder whose prevalence continues to rise globally according to reports from the World Health Organization (WHO). Early detection of diabetes risk is crucial for preventing severe long-term complications. This study aims to evaluate and compare the performance of three machine learning algorithms Support Vector Machine (SVM), Decision Tree, and Random Forest in classifying diabetes based on health indicators and lifestyle patterns. The dataset used was obtained from Kaggle, with preprocessing stages including handling missing values and normalization. Model performance was assessed using accuracy, precision, recall, and F1-score. The experimental results show that the SVM algorithm achieved the highest accuracy at 74.89%, followed by Decision Tree with 73.39%, and Random Forest with 72.41%. This research is expected to serve as a reference for developing early medical screening systems to intelligently and accurately detect diabetes risk.]]>
Copyrights © 2026
