Recently, great progress has been achieved in diabetes management through minimally invasive continuous glucose monitoring, which involves piercing the skin to identify changes in glucose levels in the interstitial fluid. Nevertheless, the development of accurate fully non-invasive glucose monitors remains a topic of great interest. This work examines the processing of data collected from a multi-sensor system, which combines millimeter-wave, near-infrared, and other auxiliary sensors’ technology, coupled with a random forest machine learning model for prediction. We investigated possible correlations between millimeter-wave, near-infrared, skin temperature, pressure data, and blood glucose values, and deployed a machine learning model for prediction. The model is based on the random forest algorithm that was trained and tested on data collected from a study involving five healthy human subjects undergoing an intravenous glucose tolerance test. Our model achieves a root mean squared error of 21.06 mg/dl and a mean absolute relative difference of 7.31% for glucose prediction in the collected clinical subjects dataset. Additionally, 96.1% of the model’s predictions fall within the clinically acceptable zones according to the Clarke error grid analysis. The preliminary results suggest that combining multiple sensor data with machine learning techniques is promising for the development of non-invasive glucose monitoring.

We reported measurement results relating to non-invasive glucose sensing using a novel multiwavelength approach that combines radio frequency and near infrared signals in transmission through aqueous glucose-loaded solutions. Data were collected simultaneously in the 37–39 GHz and 900–1800 nm electromagnetic bands. We successfully detected changes in the glucose solutions with varying glucose concentrations between 80 and 5000 mg/dl. The measurements showed for the first time that, compared to single modality systems, greater accuracy on glucose level prediction can be achieved when combining transmission data from these distinct electromagnetic bands, boosted by machine learning algorithms.

Electromagnetic (EM) biomedical sensors in the mm-wave frequency range must detect small changes in signals in the presence of tissues, which are correlated to a pathological condition. These signals, however, can suffer from artifacts due to complex EM wave interactions such as diffraction and surface wave propagation, which are often overlooked in the design phase of these sensors. This paper studies the impact of these wave phenomena on the signals transmitted and received from a pair of antennas designed to sense glucose changes via changes in transmission through a sample. Numerical simulations and controlled experiments with glucose solutions demonstrate for the first time that unwanted signal contributions from mm surface waves along the tissue can dominate the received signals but can be reduced with the use of appropriately placed absorbers around the antenna sensors. As a result, the sensitivity of such a sensing system to glucose changes is increased. This finding can be very useful in the design and development of the glucose sensor under study, as well as for other EM-based diagnostic medical applications.

Non-invasive biosensing faces major challenges due to impedance mismatch at the skin interface, which causes significant signal reflection and limits power transmission through biological tissues. In this paper, we propose and evaluate a novel, subwavelength-thick impedance-matching metasurface (MTS) designed for direct skin contact to enhance electromagnetic (EM) wave transmission in the Ka-band. Our evaluation includes controlled laboratory experiments and a first-in-human study. Using an in-house developed benchtop system, we performed transmission measurements through aqueous glucose solutions and, most importantly, through the hands of six human volunteers. Our results show that the MTS significantly enhances signal transmission into human skin tissue, yielding an average improvement of up to 5 dB in the 36–37 GHz frequency range compared to the bare-skin condition, thereby improving sensitivity for analyte detection without increasing system size or power consumption. These findings demonstrate the potential of MTS-based impedance-matching layers as practical, integrable solutions to overcome key hardware limitations in wearable biomedical sensing devices. The study represents the first human investigation of an impedance-matching MTS designed to improve microwave signal penetration for non-invasive sensing applications.