A Comparative Analysis of the Machine Learning Methods for Predicting Diabetes

Abstract

Diabetes can lead to various health problems and complications, such as cardiovascular disease, kidney damage (nephropathy), eye issues, neuropathy, and foot ailments. Therefore, early diagnosis of diabetes can be immensely beneficial in preventing the development of these conditions. Utilizing machine learning is one method to detect diabetes in individuals at an early stage. In this study, we compare the performance of nine machine-learning classification models in predicting diabetes. These models include XGBoost, gradient boosting, AdaBoost, logistic regression, decision tree, KNN, perceptron, random forest, and naïve bayes. We utilize several evaluation metrics, focusing on the f1-score, area under the curve (AUC), and computational runtime. Our comparison reveals that complex tree-based models exhibit the highest f1-score and AUC, albeit with longer execution times.