Data-Driven Machine-Learning Methods for Diabetes Risk Prediction

The study focused on using machine learning (ML) methods to predict the risk of type 2 diabetes, emphasizing the importance of early diagnosis due to the rising incidence of the disease. It employed a supervised learning approach to develop efficient risk prediction tools by analyzing common symptoms associated with diabetes. Various ML models were tested and evaluated using metrics such as Precision, Recall, F-Measure, Accuracy, and AUC, with Random Forest and K-NN models emerging as the best performers under 10-fold cross-validation and data splitting.