Machine Learning Models and Diabetes Prediction: A Comparative Analysis of Multiple Models Implementations

Diabetes has become a major health concern in contemporary society, impacting individuals across all age groups and regions. According to reports, 463 million adults between the ages of 20 and 79 had diabetes in 2019, and by the year 2045, the statistic is expected to increase to 700 million. This surge in cases poses substantial challenges to healthcare systems, leading to increased demand for medical services, higher rates of disability, and premature mortality. Numerous health issues, including nephrological issues, retinal damage, and heart disease are associated with diabetes. However, early detection and treatment can help mitigate or postpone these issues. This work implements four machine learning (ML) models such as Decision Tree, XGBoost, SVC and Gradient Boosting for grouping and projecting of diabetes disease. The experimental results show that Gradient Boosting model performs better than the other models with 93% accuracy.