Non-invasive Diabetes Detection using Metabolic Heat Conformation Technology and Heart Rate

Abstract

Screening and early detection of type 2 diabetes are important to prevent diabetic complications. Commonly, type 2 diabetes is detected by blood glucose measurement. However, the compliance for existing invasive devices is insufficient because these devices can potentially cause pain, infection, and tissue damage due to needle use. Thus, we have been developing a non-invasive diabetes detection method that uses metabolic heat conformation (MHC) technology. Our previous method using only MHC technology could not detect diabetes accurately, therefore, a novel non-invasive diabetes detection method using additional bio-signal needed to be developed to improve accuracy of early diabetes detection. Heart rate is considered as an additional bio-signal which can be measured by non-invasive devices. The previous studies report that there is a relation between heart rate and diabetes. The objective of this study is to propose a novel non-invasive diabetes detection method using both MHC technology and heart rate. The proposed method detects diabetes by machine learning technique using skin surface temperature data based on MHC technology and heart rate. In the experiment, the proposed method and our previous method were compared by using 95 samples bio-signal dataset obtained from 5 participants including 2 diabetes patients. The results showed that the proposed method could detect diabetes with accuracy higher than 90 %, which is significant improvement in comparison to our previous method, which detected diabetes with accuracy less than 80 %. The results support the possibility that the proposed method using both MHC technology and heart rate can be applied for non-invasive early diabetes detection.