The Use of Photoplethysmography for Blood Glucose Estimation by Noninvasive Method

Noninvasive blood glucose estimation system based on photoplethysmography is proposed in this paper. Photoplethysmography (PPG) is an optical technique which uses infrared light to determine the fluctuations in blood stream in the human body with every pulse. However literature reveals that, a functional correlation exists among pulse signal waveform and the glucose contents in the blood. Many researchers have shown estimation of glucose using different spectroscopy techniques which involves an optical sensor. The key involvement of this paper is withdrawal of different features with respect to time domain as well as frequency domain. Exploration of single pulse is also carried out with different features. A PPG data of 182 random people with varied health conditions like diabetic, blood pressure condition is recorded for about 1 min duration. The glucose estimation is done in two ways: the first one is feature extraction from complete PPG signal of a patient and the second one is single pulse wave analysis. All the features from above-mentioned methods are transformed into feature vector which acts as input to system and estimation of blood glucose is performed. We used Clarke Error Grid Analysis for blood glucose estimation which is clinically accepted. With time and frequency domain features we got 43.75% samples in region A and 50% samples in region B, so total 93.75% samples are in regions A and B. Using single pulse wave analysis we got 59.66% samples in region A and 34.61% samples in region B, so total 94.27% samples are in clinically accepted regions (A and B). As single pulse wave analysis shows significant improvement in region A (20% of actual blood glucose value), this method is good selection for glucose measurement.