A non-invasive glucose measurement system based on the method of metabolic heat conformation (MHC) is presented in this paper. This system consists of three temperature sensors, two humidity sensors, an infrared sensor and an optical measurement device. The glucose level can be deduced from the quantity of heat dissipation, blood flow rate of local tissue and degree of blood oxygen saturation. The methodology of the data process and the measurement error are also analyzed. The system is applied in a primary clinical test. Compared with the results of a commercial automated chemistry analyzer, the correlation coefficient of the collected data from the system is 0.856. Result shows that the correlation coefficient improves when the factor of heat dissipated by evaporation of the skin is added in. A non-invasive method of measuring the blood flow rate of local tissue by heat transmission between skin and contacted conductor is also introduced. Theoretical derivation and numerical simulation are completed as well. The so-called normalized difference mean (NDM) is chosen to express the quantity of the blood flow rate. The correlation coefficient between the blood flow rates by this method and the results of a Doppler blood flow meter is equal to 0.914.

Daily continuous glucose monitoring is very helpful in the control of glucose levels for people with diabetes and impaired glucose tolerance. In this study, a multisensor-based, noninvasive continuous glucometer was developed, which can continuously estimate glucose levels via monitoring of physiological parameter changes such as impedance spectroscopy at low and high frequency, optical properties, temperature and humidity. Thirty-three experiments were conducted for six healthy volunteers and three volunteers with diabetes. Results showed that the average correlation coefficient between the estimated glucose profiles and reference glucose profiles reached 0.8314, with a normalized root mean squared error (NRMSE) of 14.6064. The peak time of postprandial glucose was extracted from the glucose profile, and its estimated value had a correlation coefficient of 0.9449 with the reference value, wherein the root mean square error (RMSE) was 6.8958 min. Using Clarke error grid (CEG) analysis, 100% of the estimated glucose values fell in the clinically acceptable zones A and B, and 92.86% fell in zone A. The application of a multisensor-based, noninvasive continuous glucometer and time series analysis can endure the time delay between human physiological parameters and glucose level changes, so as to potentially accomplish noninvasive daily continuous glucose monitoring.