Realization of non-invasive blood glucose detector based on nonlinear auto regressive model and dual-wavelength_Journal of Biomedical Engineering

Authors：

LI Mengze ^1,2 ,  JI Zhong ¹ , CHENG Jinxiu ¹ , DU Yubao ¹ , DAI Juan ¹

1. College of Biological Engineering, Chongqing University, Chongqing 400044, P.R.China;
2. Chongqing University Cancer Hospital, Chongqing 400044, P.R.China;

Corresponding author：

JI Zhong, Email: jizhong@cqu.edu.cn

Keywords：

near-infrared light; dual-wavelength; blood glucose; non-invasive detection

DOI：

10.7507/1001-5515.201911063

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

The use of non-invasive blood glucose detection techniques can help diabetic patients to alleviate the pain of intrusive detection, reduce the cost of detection, and achieve real-time monitoring and effective control of blood glucose. Given the existing limitations of the minimally invasive or invasive blood glucose detection methods, such as low detection accuracy, high cost and complex operation, and the laser source's wavelength and cost, this paper, based on the non-invasive blood glucose detector developed by the research group, designs a non-invasive blood glucose detection method. It is founded on dual-wavelength near-infrared light diffuse reflection by using the 1 550 nm near-infrared light as measuring light to collect blood glucose information and the 1 310 nm near-infrared light as reference light to remove the effects of water molecules in the blood. Fourteen volunteers were recruited for in vivo experiments using the instrument to verify the effectiveness of the method. The results indicated that 90.27% of the measured values of non-invasive blood glucose were distributed in the region A of Clarke error grid and 9.73% in the region B of Clarke error grid, all meeting clinical requirements. It is also confirmed that the proposed non-invasive blood glucose detection method realizes relatively ideal measurement accuracy and stability.

Citation： LI Mengze, JI Zhong, CHENG Jinxiu, DU Yubao, DAI Juan. Realization of non-invasive blood glucose detector based on nonlinear auto regressive model and dual-wavelength. Journal of Biomedical Engineering, 2021, 38(2): 342-350. doi: 10.7507/1001-5515.201911063 Copy

1.	International Diabetes Federation. IDF diabetes atlas, 9th edition. Brussels: International Diabetes Federation, 2019.
2.	Vashist S K. Non-invasive glucose monitoring technology in diabetes management: A review. Analytica Chimica Acta, 2012, 750: 16-27.
3.	方旭超, 张培茗, 饶兰, 等. 连续血糖检测技术研究进展. 传感器与微系统, 2019, 38(8): 1-4.
4.	International Diabetes Federation Guideline Development Group. Global guideline for type 2 diabetes-diabetes research and clinical practice. DiabetesRes Clin Pract, 2014, 1(104): 1-52.
5.	Maruo K, Tsurugi M, Tamura M. In vivo noninvasive measurement of blood glucose by near-infrared diffuse-reflectance spectroscopy. Appl Spectrosc, 2003, 57(10): 1236-1244.
6.	Caduff A, Dewarrat F, Talary M, et al. Non-invasive glucose monitoring in patients with diabetes: a novel system based on impedance spectroscopy. Biosens Bioelectron, 2006, 22(5): 598-604.
7.	Kim Y J, Hahn S, Yoon G. Determination of glucose in whole blood samples by mid-infrared spectroscopy. Appl Opt, 2003, 42(4): 745-749.
8.	Enejder A M K, Scecina T G, Oh J, et al. Raman spectroscopy for noninvasive glucose measurements. J Biomed Opt, 2005, 10(3): 1111-1114.
9.	Lan Y T, Kuang Y P, Zhou L P, et al. Noninvasive monitoring of blood glucose concentration in diabetic patients with optical coherence tomography. Laser Phys Lett, 2017, 14(3): 35603.
10.	Khalil O S. Non-invasive glucose measurement technologies: an update from 1999 to the dawn of the new millennium. Diabet Technol Therapeut, 2004, 6(5): 660-697.
11.	Mazarevica G, Freivalds T, Jurka A. Properties of erythrocyte light refraction in diabetic patients. J Biomed Opt, 2002, 7(2): 244.
12.	Nikawa Y, Someya D, Yamamoto M. Non-invasive measurement of blood sugar level by millimeter waves// IEEE MTT-S International Microwave Symposium. Phoenix: IEEE, 2000: 171-174.
13.	Nikawa Y, Someya D. Application of millimeter waves to measure blood sugar level// Asia-Pacific Microwave Conference. Taipei: IEEE, 2001: 1303-1306.
14.	Shen Y, Lu Z, Spiers S, et al. Measurement of the optical absorption coefficient of a liquid by use of a time-resolved photoacoustic technique. Appl Opt, 2000, 39(22): 4007-4012.
15.	Evans N D, Gnudi L, Rolinski O J, et al. Non-invasive glucose monitoring by NAD(P)H autofluorescence spectroscopy in fibroblasts and adipocytes: a model for skin glucose sensing. Diabet Technol Therapeut, 2003, 5(5): 807-816.
16.	Caspers P J, Lucassen G W, Puppels G J. Combined in vivo confocal raman spectroscopy and confocal microscopy of human skin. Biophys J, 2003, 85(1): 572-580.
17.	Wang J, Carmon K S, Luck L A, et al. Electrochemical impedance biosensor for glucose detection utilizing a periplasmic E. coli receptor protein. Electrochem Solid State Lett, 2005, 8(8): H61-H64.
18.	Ermolina I, Polevaya Y, Feldman Y. Analysis of dielectric spectra of eukaryotic cells by computer modeling. Eur Biophys J, 2000, 29(2): 141-145.
19.	Gourzi M, Rouane A, Guelaz R. Study of a new electromagnetic sensor for glycaemia measurement: in vitro results on blood pig. J Med Eng Technol, 2009, 27(6): 276-281.
20.	So C F, Choi K S, Wong T K, et al. Recent advances in noninvasive glucose monitoring. Med Devices, 2012, 5(1): 45-52.
21.	Kurnik R T, Oliver J J, Waterhouse S R, et al. Application of the mixtures of experts algorithm for signal processing in a noninvasive glucose monitoring system. Sens Actuators B: Chem, 1999, 60(1): 19-26.
22.	代娟. 近红外光谱无创血糖检测模型研究. 重庆: 重庆大学, 2018.
23.	白路军. 近红外水分检测仪研究. 沈阳: 东北大学, 2013.
24.	贾浩. 散射介质中葡萄糖的等漫反射波长的存在特性及应用. 天津: 天津大学, 2012.
25.	邓斌. 有效提取近红外光谱中糖特异性信号的理论和实验研究. 天津: 天津大学, 2006.
26.	刘娴萱. 基于近红外光谱的血糖检测与分析研究. 北京: 北京邮电大学, 2017.
27.	Yadav J, Rani A, Singh V, et al. Near-infrared LED based non-invasive blood glucose sensor// International Conference on Signal Processing and Integrated Networks. Noida: IEEE, 2014: 591-594.
28.	杜玉宝. 便携式无创血糖检测仪的实现. 重庆: 重庆大学, 2018.
29.	Goodarzi M, Sharma S, Ramon H, et al. Multivariate calibration of NIR spectroscopic sensors for continuous glucose monitoring. Trac-trends Anal Chem, 2015, 67: 147-158.
30.	Yadav J, Rani A, Singh V, et al. Prospects and limitations of non-invasive blood glucose monitoring using near-infrared spectroscopy. Biomed Signal Process Control, 2015, 18: 214-227.
31.	Pastor-Bárcenas O, Soria-Olivas E, Martín-Guerrero J D, et al. Unbiased sensitivity analysis and pruning techniques in neural networks for surface ozone modelling. Ecological Modelling, 2005, 182(2): 149-158.
32.	Rumelhart D E, Hinton G E, Williams R J. Learning representations by back-propagating errors. Nature, 1986, 323(6088): 533-536.
33.	Zurada J M, Malinowski A, Cloete I. Sensitivity analysis for minimization of input data dimension for feedforward neural network// IEEE International Symposium on Circuits & Systems. London: IEEE, 1994: 447-450.
34.	Wong C X, Worden K. Generalised NARX shunting neural network modelling of friction. Mechan Syst Signal Process, 2007, 21(1): 553-572.
35.	Zhang Ping. Model selection via multifold cross validation. Ann Statist, 1993, 21(1): 299-313.
36.	Prabir B. A comparative study of ordinary cross-validation, v-fold cross-validation and the repeated learning-testing methods. Biometrika, 1989, 76(3): 503-514.
37.	代娟, 季忠, 杜玉宝. 基于粒子群和人工神经网络的近红外光谱血糖建模方法研究. 生物医学工程学杂志, 2017, 34(5): 713-720.
38.	李东明, 贾书海. 基于多光谱应用BP人工神经网络预测血糖. 激光与光电子学进展, 2017, 54(3): 244-249.
39.	Clarke W L, Cox D, Gonderfrederick L A. Evaluating clinical accuracy of systems for self-monitoring of blood glucose. Diabetes Care, 1987, 23(11): 622-628.

1. International Diabetes Federation. IDF diabetes atlas, 9th edition. Brussels: International Diabetes Federation, 2019.
2. Vashist S K. Non-invasive glucose monitoring technology in diabetes management: A review. Analytica Chimica Acta, 2012, 750: 16-27.
3. 方旭超, 张培茗, 饶兰, 等. 连续血糖检测技术研究进展. 传感器与微系统, 2019, 38(8): 1-4.
4. International Diabetes Federation Guideline Development Group. Global guideline for type 2 diabetes-diabetes research and clinical practice. DiabetesRes Clin Pract, 2014, 1(104): 1-52.
5. Maruo K, Tsurugi M, Tamura M. In vivo noninvasive measurement of blood glucose by near-infrared diffuse-reflectance spectroscopy. Appl Spectrosc, 2003, 57(10): 1236-1244.
6. Caduff A, Dewarrat F, Talary M, et al. Non-invasive glucose monitoring in patients with diabetes: a novel system based on impedance spectroscopy. Biosens Bioelectron, 2006, 22(5): 598-604.
7. Kim Y J, Hahn S, Yoon G. Determination of glucose in whole blood samples by mid-infrared spectroscopy. Appl Opt, 2003, 42(4): 745-749.
8. Enejder A M K, Scecina T G, Oh J, et al. Raman spectroscopy for noninvasive glucose measurements. J Biomed Opt, 2005, 10(3): 1111-1114.
9. Lan Y T, Kuang Y P, Zhou L P, et al. Noninvasive monitoring of blood glucose concentration in diabetic patients with optical coherence tomography. Laser Phys Lett, 2017, 14(3): 35603.
10. Khalil O S. Non-invasive glucose measurement technologies: an update from 1999 to the dawn of the new millennium. Diabet Technol Therapeut, 2004, 6(5): 660-697.
11. Mazarevica G, Freivalds T, Jurka A. Properties of erythrocyte light refraction in diabetic patients. J Biomed Opt, 2002, 7(2): 244.
12. Nikawa Y, Someya D, Yamamoto M. Non-invasive measurement of blood sugar level by millimeter waves// IEEE MTT-S International Microwave Symposium. Phoenix: IEEE, 2000: 171-174.
13. Nikawa Y, Someya D. Application of millimeter waves to measure blood sugar level// Asia-Pacific Microwave Conference. Taipei: IEEE, 2001: 1303-1306.
14. Shen Y, Lu Z, Spiers S, et al. Measurement of the optical absorption coefficient of a liquid by use of a time-resolved photoacoustic technique. Appl Opt, 2000, 39(22): 4007-4012.
15. Evans N D, Gnudi L, Rolinski O J, et al. Non-invasive glucose monitoring by NAD(P)H autofluorescence spectroscopy in fibroblasts and adipocytes: a model for skin glucose sensing. Diabet Technol Therapeut, 2003, 5(5): 807-816.
16. Caspers P J, Lucassen G W, Puppels G J. Combined in vivo confocal raman spectroscopy and confocal microscopy of human skin. Biophys J, 2003, 85(1): 572-580.
17. Wang J, Carmon K S, Luck L A, et al. Electrochemical impedance biosensor for glucose detection utilizing a periplasmic E. coli receptor protein. Electrochem Solid State Lett, 2005, 8(8): H61-H64.
18. Ermolina I, Polevaya Y, Feldman Y. Analysis of dielectric spectra of eukaryotic cells by computer modeling. Eur Biophys J, 2000, 29(2): 141-145.
19. Gourzi M, Rouane A, Guelaz R. Study of a new electromagnetic sensor for glycaemia measurement: in vitro results on blood pig. J Med Eng Technol, 2009, 27(6): 276-281.
20. So C F, Choi K S, Wong T K, et al. Recent advances in noninvasive glucose monitoring. Med Devices, 2012, 5(1): 45-52.
21. Kurnik R T, Oliver J J, Waterhouse S R, et al. Application of the mixtures of experts algorithm for signal processing in a noninvasive glucose monitoring system. Sens Actuators B: Chem, 1999, 60(1): 19-26.
22. 代娟. 近红外光谱无创血糖检测模型研究. 重庆: 重庆大学, 2018.
23. 白路军. 近红外水分检测仪研究. 沈阳: 东北大学, 2013.
24. 贾浩. 散射介质中葡萄糖的等漫反射波长的存在特性及应用. 天津: 天津大学, 2012.
25. 邓斌. 有效提取近红外光谱中糖特异性信号的理论和实验研究. 天津: 天津大学, 2006.
26. 刘娴萱. 基于近红外光谱的血糖检测与分析研究. 北京: 北京邮电大学, 2017.
27. Yadav J, Rani A, Singh V, et al. Near-infrared LED based non-invasive blood glucose sensor// International Conference on Signal Processing and Integrated Networks. Noida: IEEE, 2014: 591-594.
28. 杜玉宝. 便携式无创血糖检测仪的实现. 重庆: 重庆大学, 2018.
29. Goodarzi M, Sharma S, Ramon H, et al. Multivariate calibration of NIR spectroscopic sensors for continuous glucose monitoring. Trac-trends Anal Chem, 2015, 67: 147-158.
30. Yadav J, Rani A, Singh V, et al. Prospects and limitations of non-invasive blood glucose monitoring using near-infrared spectroscopy. Biomed Signal Process Control, 2015, 18: 214-227.
31. Pastor-Bárcenas O, Soria-Olivas E, Martín-Guerrero J D, et al. Unbiased sensitivity analysis and pruning techniques in neural networks for surface ozone modelling. Ecological Modelling, 2005, 182(2): 149-158.
32. Rumelhart D E, Hinton G E, Williams R J. Learning representations by back-propagating errors. Nature, 1986, 323(6088): 533-536.
33. Zurada J M, Malinowski A, Cloete I. Sensitivity analysis for minimization of input data dimension for feedforward neural network// IEEE International Symposium on Circuits & Systems. London: IEEE, 1994: 447-450.
34. Wong C X, Worden K. Generalised NARX shunting neural network modelling of friction. Mechan Syst Signal Process, 2007, 21(1): 553-572.
35. Zhang Ping. Model selection via multifold cross validation. Ann Statist, 1993, 21(1): 299-313.
36. Prabir B. A comparative study of ordinary cross-validation, v-fold cross-validation and the repeated learning-testing methods. Biometrika, 1989, 76(3): 503-514.
37. 代娟, 季忠, 杜玉宝. 基于粒子群和人工神经网络的近红外光谱血糖建模方法研究. 生物医学工程学杂志, 2017, 34(5): 713-720.
38. 李东明, 贾书海. 基于多光谱应用BP人工神经网络预测血糖. 激光与光电子学进展, 2017, 54(3): 244-249.
39. Clarke W L, Cox D, Gonderfrederick L A. Evaluating clinical accuracy of systems for self-monitoring of blood glucose. Diabetes Care, 1987, 23(11): 622-628.

Journal of Biomedical Engineering

Realization of non-invasive blood glucose detector based on nonlinear auto regressive model and dual-wavelength

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content