Noninvasive Glucose Prediction System Enhanced by Mixed Linear Models and Meta-Forests for Domain Generalization

In this study, we present a noninvasive glucose prediction system that integrates near-infrared (NIR) spectroscopy and millimeter-wave (mm-wave) sensing. We employ a mixed linear model (MixedLM) to analyze the association between mm-wave frequency ${S}_{{21}}$ parameters and blood glucose levels within a heterogeneous dataset. The MixedLM method considers intersubject variability and integrates multiple predictors, offering a more comprehensive analysis than traditional correlation analysis. In addition, we incorporate a domain generalization (DG) model, meta-forests, to effectively handle domain variance in the dataset, enhancing the model’s adaptability to individual differences. Our results demonstrate promising accuracy in glucose prediction for unseen subjects, with a mean absolute error (MAE) of 17.47 mg/dL, a root mean square error (RMSE) of 31.83 mg/dL, and a mean absolute percentage error (MAPE) of 10.88%, highlighting its potential for clinical application. This study marks a significant step toward developing accurate, personalized, and noninvasive glucose monitoring systems, contributing to improved diabetes management.