JMIR Publications

ABSTRACT

Background:

Prediabetes is an intermediate stage between normal glucose metabolism and diabetes and is associated with increased risk of complications like cardiovascular disease and kidney failure.

Objective:

It is crucial to recognize prediabetes individuals early in order to apply timely intervention strategies to decelerate or prohibit diabetes development.

Methods:

Multiple machine learning models are evaluated in this study, including Random Forest, XGBoost, Support Vector Machine (SVM), and K-Nearest Neighbors (KNN). For improved performance and interpretability, key clinical features were selected using Lasso Regression, including Body Mass Index (BMI), Age, LDL-C, and HDL-C. To optimize model accuracy and reduce overfitting, we employed hyperparameter tuning with RandomizedSearchCV for XGBoost and Random Forest and GridSearchCV for SVM, and KNN. To resolve data imbalance, Synthetic Minority Oversampling Technique (SMOTE) was applied to ensure reliable classifications.

Results:

A cross-validated ROC-AUC score of 0.9117 highlighted the robustness of Random Forest in generalizing across datasets among the models tested. XGBoost followed closely, providing balanced accuracy in distinguishing between normal and prediabetes cases. While SVMs and KNNs performed adequately as baseline models, they exhibited limitations in sensitivity.

Conclusions:

It is demonstrated in this research that optimized machine learning models, especially Random Forest and XGBoost, are effective tools for assessing early prediabetes risk. Future directions include validating these models in diverse clinical settings and integrating additional biomarkers to improve prediction accuracy, offering a promising avenue for early intervention and personalized treatment strategies in preventive healthcare.