Blood glucose prediction based on imagingphotoplethysmography in combination with Machine learning. (January 2023)

• Record Type: Journal Article
• Authors: Nie, Zihan; Rong, Meng; Li, Kaiyang
• Is Part Of: Biomedical signal processing and control. Volume 79(2023)Part 2
• Publication Date: 2023-01
• Subjects: Machine learning -- Blood glucose -- Imaging photoplethysmography (IPPG) -- Near-infrared light; BG blood glucose -- PPG photoplethysmography -- IPPG imaging photoplethysmography -- NIBG non-invasive blood glucose -- NCBG non-contact blood glucose -- OGTT oral glucose tolerance test -- ROI region of interest -- ALS asymmetric least-squares -- KTE Kaiser-Teager energy -- PCR principle component regression -- PLS partial least-squares regression -- SVR support vector regression -- RFR random forest regression -- RBF radial basis function -- STD standard deviation -- MAE mean absolute error -- ME mean bias -- ECG electrocardiograph -- FPS frames per second -- MLR multiple linear regression -- MLP multi-layer perceptron; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2022.104179
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: Non-contact blood glucose estimation method has been developed based on machine learning using Imaging Photoplethysmography (IPPG) characteristic features. As the machine learning algorithms, Principle Component Regression (PCR), Partial Least-Squares Regression (PLS), Support Vector Regression (SVR) and Random Forest Regression (RFR) are used. The results show the applicability of the method into estimating blood glucose. Abstract: At present, the mainstream blood glucose detection methods are invasive, which will cause harm to the human body and make it inconvenient to measure. The non-contact measurement method can avoid these problems. In this paper, a non-contact blood glucose detection method based on a near-infrared camera is proposed. Blood glucose has a strong absorption capacity in the near-infrared band, and other components in blood (water, hemoglobin, etc.) have different absorption characteristics in this band compared with blood glucose. Therefore, in this method, we realize blood glucose detection by receiving the near-infrared light reflected back after blood glucose absorption. We extracted 26 pulse wave features from the pulse wave and analyzed 6 that were highly correlated with blood glucose. Then, four kinds of machine learning algorithms (PCR, PLS, SVR, RFR) were used to build models respectively, and the RFR with the best performance was selected to build the final blood glucose prediction model. Finally, the experimental results are analyzed by Clark error grid analysis, which shows that the proposed method is in good agreement with the reference glucose monitor. Compared with traditional invasive blood glucose detection methods, the non-contact blood glucose detection method has more application prospects.