| abstract |
The system and method disclosed in the present invention estimate the HbA1C (glycosylated hemoglobin) and blood glucose values in a non-invasive manner, which is achieved by using a multi-stage model and taking into consideration the physiological state factors of the subject. In one embodiment, the physiological state is defined by a combination of two or more physiological factors, such as a fasting or postprandial state, and whether the subject is receiving diabetes medication. In one embodiment, the model used to estimate HbA1C and blood glucose is a non-linear model, and in the second stage of the multi-stage model, whether the subject tends to obtain higher, normal, or lower HbA1C Or blood glucose estimation results, and in the third stage of the multi-stage model, the second stage model is personalized for the subjects to ensure the accuracy of the estimation. |