Beyond the Blood Draw: Explainable Machine Learning for Non-Invasive Dysglycemia Risk Screening

2026-06-14

AI Summary

This study addresses the challenge of missed diagnoses in prediabetes and diabetes due to the lack of noninvasive screening tools by developing a machine learning model that assesses dysglycemia risk without requiring laboratory tests. Leveraging large-scale NHANES population data, the authors trained and evaluated six algorithms—including LightGBM—using stratified five-fold cross-validation and SHAP interpretability analysis. The resulting model achieves high accuracy (AUC = 0.820), outperforming existing clinical risk scores, while remaining fully noninvasive and clinically interpretable. It demonstrates robust performance across diverse demographic subgroups, making it well-suited for community-based screening and self-assessment settings.

Abstract

Dysglycemia, encompassing both prediabetes and diabetes, affects huge numbers of adults worldwide, yet many of them remain undiagnosed. We developed and validated machine-learning (ML) models for non-invasive screening of dysglycemia risk that require no laboratory tests. Pooling data from the National Health and Nutrition Examination Survey (NHANES) 2017--2023 (n=14,352), we trained six ML models with stratified 5-fold cross-validation and compared them with two established clinical risk scores. LightGBM achieved the highest area under the receiver operating characteristic curve (AUC=0.820, 95% CI: 0.806--0.835), outperforming the Finnish Diabetes Risk Score (0.745) and American Diabetes Association Risk Test (0.783). SHAP analysis identified age, race/ethnicity, and waist-to-height ratio as the most influential predictors. Subgroup analyses confirmed consistent performance across demographic strata (AUC: 0.735--0.832). These results demonstrate the feasibility of explainable, laboratory-free dysglycemia screening for deployment in community settings and self-tracking health applications.

Problem

• dysglycemia
• non-invasive screening
• machine learning
• prediabetes
• diabetes risk

Innovation

• explainable machine learning
• non-invasive screening
• dysglycemia risk prediction
• LightGBM
• SHAP analysis