Published Paper Details:

This Research evaluates the effectiveness of various ML techniques applied to early detection of Diabetes through clinical diagnostic data. Algorithms Including Decision Trees and Random Forests, Support Vector Machines (SVM), K-Nearest Neighbors (KNN), Naive Bayes, and Logistic Regression were analyzed Evaluated through metrics like accuracy, precision, and recall, F1-score, and computational effectiveness. The dataset includes features like glucose levels, BMI, and blood pressure. Data preparation included addressing missing data, standardizing values, and selecting relevant features. Results indicate that Random Forest and SVM yielded the highest predictive performance, while Logistic Regression offered better model interpretability. The study underscores the trade-offs between accuracy and explainability in model selection for early diabetes detection, with suggestions for future work involving real-time data integration and advanced deep learning methods.