In addition to the damage it can cause to various organs, diabetes mellitus (DM) also increases a person's risk of developing other serious health conditions. These can include heart disease, stroke, and nerve damage. Furthermore, DM is a leading cause of blindness and kidney failure. However, with proper management and treatment, many of the complications of DM can be prevented or delayed. Thus, early detection and treatment of DM are crucial. With the advancement of machine learning technology, new opportunities have emerged in the field of medicine. Many disease detection research rely on machine learning techniques, with a particular emphasis on boosting algorithms. Boosting algorithms are used to improve the accuracy of predictions made by other weak models such as decision trees. Using knowledge discovery methods, boosting algorithms are examined and compared on a diabetes dataset in this study. The performance of the boosting algorithms is evaluated by generating ROC curves and comparing average accuracy values. When the study's results were evaluated in terms of precision, Gradient Boosting, AdaBoost, CatBoost, LightGBM, and XGBoost algorithms gives success rates of %85, %83, %88, %86, and %87, respectively.

No abstract