Early detection of diabetes based on skin impedance spectrogram and heart rate variability noninvasively

The autonomic nervous system is highly affected by the Diabetic Autonomic Neuropathy (DAN) which can also change various metabolic transitions. This causes changes in heart rate as well as in skin impedance. The objective of this work is to determine the impact of Diabetes on Heart Rate Variability (HRV) and skin impedance changes. The galvanic skin resistance or skin impedance measurement and heart rate variability analysis acts as markers for the detection of diabetes. As the heart rate variability is not able predict the diabetes at early stage we are experimenting to detect the diabetes at early stage by using the bio impedance method. For skin impedance measurement we measure galvanic skin response of 11 diabetic patients and 8 normal controls and for heart rate variability analysis we acquire ECG signals from 20 normal controls and 20 diabetic patients. Our study proposes a method based on features on galvanic skin response (GSR) such as Welch's Power spectral density estimation. To classify GSR signals we use Artificial Neural Network (ANN) algorithm, which gives an accuracy of 100%. We have also seen that there is a significant reduction in various parameters associated to Heart Rate Variability (HRV) with the development of diabetes mellitus. The HRV is analyzed using Kubios software (version 2.2). This paper proposes a design for a novel non-invasive glucose monitoring system based on the principle of skin impedance spectrogram and heart rate variability analysis.