Diabetes Prediction and Classification Using Support Vector Machine and Decision Tree Algorithms

Diabetes is a common metabolic disease that requires early identification and treatment to prevent serious complications. Machine learning (ML) developments have demonstrated a great deal of promise for improving the forecast of the start of diabetes. This study examines how well Support Vector Machine (SVM) and Decision Tree algorithms predict diabetes using the Pima Indian Diabetes dataset, which contains characteristics including body mass index, insulin, and glucose levels. Both algorithms were examined and assessed using recall, accuracy, and precision criteria. According to the results, the SVM algorithm performed better than the Decision Tree, attaining a precision of 83.05% as opposed to 76.5%. These results highlight the Support Vector Machine's potential to assist in and detect early diagnosis and management of diabetes and demonstrate how successful it is as a predictive tool. The study emphasizes the role of machine learning in healthcare and the inevitability of continuous developments in predictive modeling.