Physics-Informed Neural Networks vs. Physics Models for Non-Invasive Glucose Monitoring: A Comparative Study Under Realistic Synthetic Conditions

Non-invasive glucose monitoring remains a long-standing challenge in biomedical sensing, with the potential to transform diabetes management by eliminating painful finger pricks, reducing consumable costs, and enabling real-time glucose tracking. Despite decades of research, no solution has matched the accuracy and reliability of invasive methods in real-world deployment. Near-infrared (NIR) spectroscopy -- leveraging glucose's absorption features in the 850-1150 nm range -- remains the most promising modality, but progress has stalled due to the problem's intrinsic complexity. At its core, non-invasive glucose monitoring is an ill-posed inverse problem. The NIR signal measured at the skin surface reflects a convoluted mixture of tissue scattering, overlapping spectral absorption from water, hemoglobin, and fat, and variations in skin thickness, perfusion, and melanin content. These physiological variables are compounded by hardware noise (e.g., ADC quantization, LED instability, photodiode dark current) and environmental drift (e.g., temperature, humidity, ambient light). In the field, these effects suppress glucose-NIR correlation to ρ 0.21, rendering many lab-trained models ineffective. 1