EMD-Based Noninvasive Blood Glucose Estimation from PPG Signals Using Machine Learning Algorithms

Abstract

Effective management of diabetes requires accurate monitoring of blood glucose levels. Traditional invasive methods for such monitoring can be cumbersome and uncomfortable for patients. In this study, we introduce a noninvasive approach to estimate blood glucose levels using photoplethysmography (PPG) signals. We have focused on blood glucose prediction using wrist PPG signals and explored various PPG waveform-based features, including AC to DC ratio (AC/DC) and intrinsic mode function (IMF)-based features derived from empirical mode decomposition (EMD). To the best of our knowledge, no studies have been found using EMD-based features to estimate blood glucose levels noninvasively. Additionally, feature importance-based selection has also been used to further improve the accuracy of the proposed model. Among the four machine learning algorithms considered in this study, CatBoost consistently outperformed XGBoost, LightGBM, and random forest across a wide number of features. The best performing model, CatBoost, achieved Pearson’s r of 0.96, MSE 0.08, R2 score 0.92, and MAE 8.01 when considering the top 50 features selected from both PPG waveform-based features and IMF-based features. The p-values for all models were <0.001, indicating statistically significant correlations. Overall, this study provides valuable insights into the feasibility and effectiveness of noninvasive blood glucose monitoring using advanced machine learning techniques.

Keywords

• photoplethysmography
• blood glucose
• diabetes
• machine learning
• empirical mode decomposition