Reliable Noninvasive Glucose Sensing via CNN-Based Spectroscopy
This provides a potential solution for reliable continuous glucose monitoring in diabetic patients, though it appears incremental as it builds on existing spectroscopy and AI methods.
The study tackled non-invasive glucose sensing by developing a dual-modal AI framework using SWIR spectroscopy, achieving a MAPE of 4.82% with CNN and 86.4% Zone A accuracy with a photodiode system on synthetic phantoms.
In this study, we present a dual-modal AI framework based on short-wave infrared (SWIR) spectroscopy. The first modality employs a multi-wavelength SWIR imaging system coupled with convolutional neural networks (CNNs) to capture spatial features linked to glucose absorption. The second modality uses a compact photodiode voltage sensor and machine learning regressors (e.g., random forest) on normalized optical signals. Both approaches were evaluated on synthetic blood phantoms and skin-mimicking materials across physiological glucose levels (70 to 200 mg/dL). The CNN achieved a mean absolute percentage error (MAPE) of 4.82% at 650 nm with 100% Zone A coverage in the Clarke Error Grid, while the photodiode system reached 86.4% Zone A accuracy. This framework constitutes a state-of-the-art solution that balances clinical accuracy, cost efficiency, and wearable integration, paving the way for reliable continuous non-invasive glucose monitoring.