Diabetes Prediction Using Traditional Machine Learning Techniques

This study examines the capability of traditional machine learning (ML) algorithms to predictthe onset of diabetes using the Pima Indians diabetes dataset. It employed decision trees, naivebayes, k-Nearest Neighbors (kNN), and logistic regression classifiers were evaluated using theperformance metrics of accuracy, precision, recall, F1 score and ROC AUC. The data was preprocessedto amend implausible values and stratified sampling was performed to facilitatebalancing classes when splitting the data. The naive bayes algorithm achieves the best accuracy(72.7%) while logistic regression obtains the best class separability (ROC AUC of 0.813). Theproject shows that interpretable models can provide actionable insights for early identification,supporting Sustainable Development Goal 3 (Good Health and Well-Being), particularly bypromoting preventive healthcare and informed decision-making in resource-constrainedenvironments.