Authors: Associates Professor K.Jagadeesh,, K Sravanthi, M Charanya, M Deepika Veera Naga Rajyalakshmi,, G Vineetha Raj
Abstract: Diabetes mellitus is one of the most prevalent chronic diseases worldwide, posing significant health and economic challenges. Early prediction of diabetes can greatly assist in timely diagnosis and effective management of the disease. This study presents a machine learning– based approach for predicting the likelihood of diabetes using clinical and physiological data. The dataset was preprocessed through normalization and feature selection to improve model efficiency. Various supervised learning algorithms, including Logistic Regression, Decision Tree, Random Forest, and Support Vector Machine (SVM), were implemented and evaluated based on accuracy, precision, recall, and F1-score. Among these, the Random Forest classifier demonstrated superior performance with the highest overall accuracy, indicating its robustness in handling complex, non-linear relationships among features. The results suggest that predictive modelling using machine learning can serve as a valuable tool to support healthcare professionals in identifying individuals at high risk of developing diabetes. Future work will focus on incorporating larger and more diverse datasets and exploring deep learning models to further enhance predictive accuracy and reliability.
