@article{article_1632130, title={The Role of Machine Learning Models in Early Diabetes Diagnosis: A Dataset Based Analysis}, journal={Computer Science}, volume={10}, pages={33–42}, year={2025}, DOI={10.53070/bbd.1632130}, author={Çengel, Ekemen and Cengil, Emine and Yıldırım, Muhammed}, keywords={Diyabet, Makine Öğrenmesi, BIT Mesra Veri kümesi, Pima Indian Veri Kümesi, Yapay Zeka}, abstract={Diabetes is a chronic metabolic disease in which the level of glucose in the blood rises above normal. The main reason for this is that the pancreas cannot produce enough insulin or the insulin produced cannot be used effectively. For diabetes to be managed and complications to be avoided, early diagnosis is essential. Advanced technologies such as machine learning contribute to both individual health management and public health systems by providing high accuracy rates in early diagnosis. In this study, it is aimed to examine the role of machine learning methods in the early diagnosis of diabetes. For this purpose, the methods were analysed on two different datasets. Support Vector Machines, Decision Trees, and Artificial Neural Networks were among the machine learning classifiers that were employed. In both datasets, the performance of the models in terms of metrics such as accuracy, sensitivity, and specificity were evaluated and compared. According to the results, the Bagged Trees algorithm showed the best performance with 96.2% in the first dataset we used, BIT Mesra Dataset. In the Pima Indian dataset, the SVM algorithm achieved an accuracy rate of 77.2%. The study provides a method for early diagnosis of diabetes, and emphasises the importance of data diversity in this field.}, number={1}, publisher={Ali KARCI}