Key result
Photoplethysmography-based machine learning achieves ~91% accuracy for non-invasive diabetes classification.
Why the study?
Diabetes affects over 537 million adults globally, and early detection is critical for preventing complications.
Does a machine learning framework using PPG signals accurately classify diabetes?
Does a machine learning framework using PPG signals accurately classify diabetes?
A machine learning framework utilizing PPG signals and TreeSHAP feature selection demonstrates high accuracy for non-invasive diabetes screening, offering a viable tool for resource-limited settings.
May support PPG-based ML for non-invasive diabetes screening; hypothesis-generating and requires prospective validation before clinical adoption.
Diabetes affects over 537 million adults globally, with early detection critical for preventing complications. This study develops a comprehensive machine learning framework for non-invasive diabetes screening using photoplethysmography (PPG) signals integrated with clinical metadata. We systematically evaluated ten digital filtering techniques across two independent datasets, namely the Guilin PPG-BP and Mazandaran datasets. The Adaptive Butterworth filter achieved optimal performance for Guilin data where SNR was 31.59 dB, while DC Removal with HP and LP Cascade excelled for Mazandaran where SNR was 22.50 dB, demonstrating dataset-specific filtering requirements. Comprehensive feature extraction generated 38 physiological features spanning time-domain, frequency-domain, morphological, and variability characteristics. TreeSHAP analysis identified seven key predictive features, with AI_Surrogate having SHAP importance of 0.926 and SDPPG ratios emerging as robust biomarkers. Five machine learning algorithms were optimized through hyperparameter tuning and SMOTE-based class balancing. On the Guilin dataset, the Ensemble Voting Classifier delivered the best results, achieving 90.91% accuracy, 100% precision, 77.78% recall, and a ROC-AUC of 0.915. On the Mazandaran dataset, models reached up to 90% accuracy. A Gradio-based web application demonstrated real-time prediction capability with a 0.043 s latency, providing clinicians with interpretable diabetes risk assessment. This framework establishes PPG-based screening as a viable non-invasive alternative for diabetes detection in resource-limited settings.
No takes yet. Share an insight, caveat, or question.
Singha et al. (2026) studied Diabetes. Machine learning framework using photoplethysmography (PPG) signals was evaluated on Diabetes classification accuracy. A machine learning framework using photoplethysmography signals achieved 90.91% accuracy and a ROC-AUC of 0.915 for non-invasive diabetes classification on the Guilin dataset.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: