What question did this study set out to answer?

This research aims to compare various machine learning algorithms for their effectiveness in predicting early type 2 diabetes.

April 23, 2026Open Access

A Comparative Evaluation Of Machine Learning Algorithms For Early Detection Of Type 2 Diabetes

Key Points

This research aims to compare various machine learning algorithms for their effectiveness in predicting early type 2 diabetes.
Evaluated seven supervised machine learning classifiers using two diabetes datasets.
Applied SMOTE for class imbalance and conducted stratified 10-fold cross-validation.
Assessed model performance using metrics such as accuracy, precision, and ROC-AUC.
XGBoost exhibited superior performance with AUC scores of 0.901 on PIDD and 0.951 on FHDD.
Logistic Regression maintained notable interpretability for clinical application.
Identified fasting plasma glucose, BMI, and HbA1c as key predictive features.

Abstract

This paper presents a comparative evaluation of seven supervised ML classifiers Logistic Regression, Naive Bayes, k-Nearest Neighbors, Decision Tree, Random Forest, XGBoost, and SVM for early Type 2 diabetes (T2DM) prediction. Using the Pima Indians Diabetes Database (PIDD, n=768) and Frankfurt Hospital Diabetes Dataset (FHDD, n=2000), we apply standardized preprocessing with SMOTE-based class imbalance correction and stratified 10-fold cross-validation1. Models are evaluated on Accuracy, Precision, Recall, F1-Score, ROC-AUC, and MCC. Results show XGBoost consistently outperforms all classifiers (AUC: 0.901 PIDD, 0.951 FHDD), while Logistic Regression retains interpretability advantages for clinical deployment. Feature importance analysis identifies fasting plasma glucose, BMI, and HbA1c as top predictors, aligning with clinical guidelines.

A Comparative Evaluation Of Machine Learning Algorithms For Early Detection Of Type 2 Diabetes

Key Points

Abstract

Cite This Study