基于可穿戴设备的血糖数据采集、处理和预测研究综述
A Review of Research on Blood Glucose Data Collection, Processing and Prediction Based on Wearable Devices
摘要: 随着我国人口老龄化形式日益严峻，糖尿病已经成为危害老年人身体健康的重要因素，而血糖检测是血糖管控的重要手段，目前，基于可穿戴设备采集血糖数据，利用人工智能技术实现血糖预测是未来发展的趋势。本文首先从血糖数据采集方式展开综述，分别介绍了侵入式和接触式采集的特点，其次论述了可穿戴设备血糖数据预处理方法，并分析了其优缺点，然后对国内外血糖预测技术进行总结，最后探讨了基于可穿戴设备的血糖数据采集、处理和预测技术所面临的问题以及未来的发展趋势。
Abstract: With the increasingly severe form of population aging in my country, diabetes has become an im-portant factor that endangers the health of the elderly, and blood sugar detection is an important means of blood glucose control. Based on wearable devices to collect blood glucose data and use artificial intelligence technology to achieve blood glucose prediction is the future development trend. This paper firstly summarizes the methods of blood glucose data collection, introduces the characteristics of invasive and contact collection, and then discusses the preprocessing method of blood glucose data of wearable devices, and analyzes its advantages and disadvantages, and then summarizes the domestic and foreign blood glucose prediction technologies, and finally discusses the problems and future development trends of blood glucose data collection, processing and pre-diction technology based on wearable devices.
文章引用：刘赛赛, 杨观赐. 基于可穿戴设备的血糖数据采集、处理和预测研究综述[J]. 软件工程与应用, 2022, 11(4): 721-730. https://doi.org/10.12677/SEA.2022.114075

参考文献

[1] Zhang, Y., Sun, J., Liu, L., et al. (2021) A Review of Biosensor Technology and Algorithms for Glucose Monitoring. Journal of Diabetes and its Complications, 35, Article ID: 107929. [Google Scholar] [CrossRef] [PubMed]
[2] Hidalgo, J., Colmenar, J., Kronberger, G., et al. (2017) Data Based Prediction of Blood Glucose Concentrations Using Evolutionary Methods. Journal of Medical Systems, 41, 1-20. [Google Scholar] [CrossRef] [PubMed]
[3] Oviedo, S., Vehí, J., Calm, R., et al. (2017) A Review of Per-sonalized Blood Glucose Prediction Strategies for T1DM Patients. International Journal for Numerical Methods in Biomedical Engineering, 33, Article ID: e2833. [Google Scholar] [CrossRef] [PubMed]
[4] Motoaki, S., Nobuyuki, A., Yoshimitsu, Y., et al. (1986) Telemetry Glucose Monitoring Device with Needle-Type Glucose Sensor: A Useful Tool for Blood Glucose Monitoring in Diabetic Individuals. Diabetes Care, 9, 298-301. [Google Scholar] [CrossRef] [PubMed]
[5] Sanjiv, S., Reddy, M. and Jugnee, N. (2018) A Pilot Study in Humans of Microneedle Sensor Arrays for Continuous Glucose Monitoring. Analytical Methods, 10, 2088-2095. [Google Scholar] [CrossRef] 
[6] Li, X., Huang, X. and Mo, J. (2021) A Fully Integrated Closed-Loop System Based on Mesoporous Microneedles-Iontophoresis for Diabetes Treatment. Advanced Science, 8, Article ID: e2100827. [Google Scholar] [CrossRef] [PubMed]
[7] Pu, Z., Zhang, X., Yu, H., et al. (2021) A Thermal Activated and Differential Self-Calibrated Flexible Epidermal Biomicrofluidic Device for Wearable Accurate Blood Glucose Monitoring. Science Advances, 7, Article ID: eabd0199. [Google Scholar] [CrossRef] [PubMed]
[8] Hakjae, L., Bonfante, G., Sasaki, Y., et al. (2020) Porous Microneedles on a Paper for Screening Test of Prediabetes. Medical Devices & Sensors, 3, Article ID: e10109. [Google Scholar] [CrossRef] 
[9] Bidonde, J., Fagerlund, B.C., Frønsdal, K.B., et al. (2005) FreeStyle Libre Flash Glucose Self-Monitoring System: A Single-Technology Assessment.
https://www.ncbi.nlm.nih.gov/books/NBK482068/
[10] Dexcom (n.d.) Dexcom Continuous Glucose Monitoring.
https://www.dexcom.com/g6-cgm-system
[11] Mazze, R.S., Strock, E., Borgman, S., et al. (2009) Evaluating the Accuracy, Reliability, and Clinical Applicability of Continuous Glucose Monitoring (CGM): Is CGM Ready for Real Time? Diabetes Diabetes Technology & Therapeutics, 11, 11-18. [Google Scholar] [CrossRef] [PubMed]
[12] Sparacino, G., Facchinetti, A., Cobelli, C., et al. (2010) “Smart” Con-tinuous Glucose Monitoring Sensors: On-Line Signal Processing Issues. Sensors, 10, 6751-6772. [Google Scholar] [CrossRef] [PubMed]
[13] Tierney, M., Tamada, J.A., Potts, O.R., et al. (2000) The Gluco Watch Biographer: A Frequent Automatic and Noninvasive Glucose Monitor. Annals of Medicine, 32, 632-641. [Google Scholar] [CrossRef] [PubMed]
[14] Hanna, J., Bteich, M., Tawk, Y., et al. (2020) Noninvasive, Wearable, and Tunable Electromagnetic Multisensing System for Continuous Glucose Monitoring, Mimicking Vascu-lature Anatomy. Science Advances, 6, Article No. a5320. [Google Scholar] [CrossRef] [PubMed]
[15] Lipson, J., Bernhardt, J., Block, U., et al. (2009) Non-Invasive Technologies for Glucose Monitoring: Requirements for Calibration Innoninvasive Glucose Monitoring by Raman Spectroscopy. Journal of Diabetes Science and Technology, 3, 233-241. [Google Scholar] [CrossRef] [PubMed]
[16] Lee, H., Choi, T., Lee, Y.B., et al. (2016) A Graphene-Based Electrochemical Device with Thermoresponsive Microneedles for Diabetes Monitoring and Therapy. Nature Nano-technology, 11, 566-572. [Google Scholar] [CrossRef] [PubMed]
[17] Zhu, X., Ju, Y., Chen, J., et al. (2018) Nonenzymatic Wearable Sensor for Electrochemical Analysis of Perspiration Glucose. ACS Sensors, 3, 1135-1141. [Google Scholar] [CrossRef] [PubMed]
[18] Zhu, J., Liu, S., Hu, Z., et al. (2021) Laser-Induced Graphene Non-Enzymatic Glucose Sensors for On-Body Measurements. Biosensors and Bioelectronics, 193, Article ID: 113606. [Google Scholar] [CrossRef] [PubMed]
[19] 孙甬. 揭秘谷歌测血糖隐形眼镜内置上万天线[DB/OL].
https://ihealth.dxy.cn/article/67286, 2022-8-1.
[20] Breton, M. and Kovatchev, B. (2008) Analysis, Modeling, and Simulation of the Accuracy of Continuous Glucose Sensors. Journal of Diabetes Science and Technology, 2, 853-862. [Google Scholar] [CrossRef] [PubMed]
[21] Lunn, D., Wei, C., Hovorka, R., et al. (2011) Fitting Dynamic Models with Forcing Functions: Application to Continuous Glucose Monitoring in Insulin Therapy. Statistics in Medicine, 30, 2234-2250. [Google Scholar] [CrossRef] [PubMed]
[22] Facchinetti, A., Del Favero, S., Sparacino, G., et al. (2015) Model of Glucose Sensor Error Components: Identification and Assessment for New Dexcom G4 Generation Devices. Medical & Biological Engineering & Computing, 53, 1259-1269. [Google Scholar] [CrossRef] [PubMed]
[23] Vettoretti, M., Battocchio, C., Sparacino, G., et al. (2019) De-velopment of an Error Model for a Factory-Calibrated Continuous Glucose Monitoring Sensor with 10-Day Lifetime. Sensors, 19, Article No. 5320. [Google Scholar] [CrossRef] [PubMed]
[24] Jia, Z., Huang, L., Liu, H., et al. (2020) Design of a Real-time Self-adjusting Calibration Algorithm to Improve the Accuracy of Continuous Blood Glucose Monitoring. Applied Bi-ochemistry and Biotechnology, 190, 1163-1176. [Google Scholar] [CrossRef] [PubMed]
[25] Turksoy, K., Roy, A., Cinar, A., et al. (2017) Real-Time Mod-el-Based Fault Detection of Continuous Glucose Sensor Measurements. IEEE Transactions on Biomedical Engineering, 64, 1437-1445. [Google Scholar] [CrossRef] 
[26] Quan, S., Qin, J., Doniger, K., et al. (2010) Online Dropout Detection in Subcutaneously Implanted Continuous Glucose Monitoring. Proceedings of the 2010 American Control Conference, Baltimore, 30 June-2 July 2010, 4373-4378. [Google Scholar] [CrossRef] 
[27] Rabby, M., Tu, Y., Hossen, M., et al. (2021) Stacked LSTM Based Deep Recurrent Neural Network with Kalman Smoothing for Blood Glucose Prediction. BMC Medical Infor-matics and Decision Making, 21, Article No. 101. [Google Scholar] [CrossRef] [PubMed]
[28] Xie, J. and Wang, Q. (2020) Benchmarking Machine Learning Algorithms on Blood Glucose Prediction for Type I Diabetes in Comparison with Classical Time-Series Models. IEEE Transactions on Biomedical Engineering, 67, 3101-3124. [Google Scholar] [CrossRef] 
[29] Leala, Y., Ruizb, M., Lorencio, C., et al. (2013) Principal Component Analysis in Combination with Case-Based Reasoning for Detecting Therapeutically Correct and Incorrect Measurements in Continuous Glucose Monitoring Systems. Biomedical Signal Processing and Control, 8, 603-614. [Google Scholar] [CrossRef] 
[30] Meneghetti, L., Facchinetti, A., Favero, S., et al. (2021) Model-Based Detection and Classification of Insulin Pump Faults and Missed Meal Announcements in Artificial Pancreas Systems for Type 1 Diabetes Therapy. IEEE Transactions on Biomedical Engineering, 68, 170-180. [Google Scholar] [CrossRef] 
[31] Xia, Y., Sun, X., Zhao, Y., et al. (2020) Fault Detection of Continuous Glucose Measurements Based on Modified k-Medoids Clustering Algorithm. Neural Computing and Applications. [Google Scholar] [CrossRef] 
[32] 周玉, 朱文豪, 房倩, 白磊. 基于聚类的离群点检测方法研究综述[J]. 计算机工程与应用, 2021, 57(12): 37-45.
[33] Angkhawey, U. and Muangsin, V. (2018) Detecting Points of Interest in a City from Taxi GPS with Adaptive DBSCAN. 2018 7th ICT International Student Project Conference (ICT-ISPC), Nakhonpathom, 11-13 July 2018, 1-6. [Google Scholar] [CrossRef] 
[34] Lim, S., Lee, S., Kim, S., et al. (2018) Clustering of Detected Targets Using DBSCAN in Automotive Radar Systems. 2018 19th International Radar Symposium (IRS), Bonn, 20-22 June 2018, 1-7. [Google Scholar] [CrossRef] 
[35] Gu, W., Zhou, Z., Zhou, Y., et al. (2017) Predicting Blood Glu-cose Dynamics with Multi-Time-Series Deep Learning. 15th Symposium on Neural Networks and Applications (NEUREL), Belgrade, 6-8 November 2017, Article No. 55. [Google Scholar] [CrossRef] 
[36] Bergman, R., Phillips, L., Cobelli, C., et al. (1981) Physiologic Evaluation of Factors Controlling Glucose Tolerance in Man: Measurement of Insulin Sensitivity and Beta-Cell Glucose Sensitivity from the Response to Intravenous Glucose. Journal of Clinical Investigation, 68, 1456-1467. [Google Scholar] [CrossRef] 
[37] Cobelli, C., Toffolo, G. and Ferrannini, E. (1984) A Model of Glucose Kinetics and Their Control by Insulin, Compartmental and Noncompartmental Approaches. Mathematical Biosciences, 72, 291-315. [Google Scholar] [CrossRef] 
[38] Sorensen, Thomas, J. (1985) A Physiologic Model of Glucose Metabolism in Man and Its Use to Design and Assess Improved Insulin Therapies for Diabetes. Massachusetts Institute of Technology, Cambridge, 497-528.
[39] Hovorka, R., Shojaee, M., Carroll, P., et al. (2002) Partitioning Glucose Distribution/Transport, Disposal, and Endogenous Production during IVGTT. American Journal of Physiology-Endocrinology and Metabolism, 282, E992-E1007. [Google Scholar] [CrossRef] [PubMed]
[40] Wilinska, M., Chassin, L., Schaller, H., et al. (2005) Insulin Kinetics in Type-I Diabetes: Continuous and Bolus Delivery of Rapid Acting Insulin. IEEE Transactions on Biomedical Engineering, 52, 3-12. [Google Scholar] [CrossRef] 
[41] Dalla, M., Rizza, R., Cobelli, C., et al. (2007) Meal Simulation Model of the Glucose-Insulin System. IEEE Transactions on Biomedical Engineering, 54, 1740-1749. [Google Scholar] [CrossRef] 
[42] Roy, A. and Parker, R. (2006) Mixed Meal Modeling and Disturbance Rejection in Type I Diabetic Patients. 2006 International Conference of the IEEE Engineering in Medicine and Biology Society, New York, 30 August-3 September 2006, 323-326. [Google Scholar] [CrossRef] 
[43] Woldaregay, A., Årsand, E., Walderhaug, S., et al. (2019) Data-Driven Modeling and Prediction of Blood Glucose Dynamics: Machine Learning Applications in Type 1 Diabetes. Artificial Intelligence in Medicine, 98, 109-134. [Google Scholar] [CrossRef] [PubMed]
[44] Georga, E., Príncipe, J., Fotiadis, D., et al. (2019) Short-Term Prediction of Glucose in Type 1 Diabetes Using Kernel Adaptive Filters. Medical & Biological Engineering & Computing, 57, 27-46. [Google Scholar] [CrossRef] [PubMed]
[45] Saiti, K., Macaš, M., Lhotská, L., et al. (2020) Ensemble Methods in Combination with Compartment Models for Blood Glucose Level Prediction in Type 1 Diabetes Mellitus. Computer Methods and Programs in Biomedicine, 196, Article ID: 105628. [Google Scholar] [CrossRef] [PubMed]
[46] Li, K., Liu, C., Zhu, T., et al. (2020) GluNet: A Deep Learning Framework for Accurate Glucose Forecasting. IEEE Journal of Biomedical and Health Informatics, 24, 414-423. [Google Scholar] [CrossRef] 
[47] Munoz-Organero, M. (2020) Deep Physiological Model for Blood Glucose Prediction in T1DM Patients. Sensors, 20, Article No. 3896. [Google Scholar] [CrossRef] [PubMed]
[48] Mhaskar, H. and Pereverzyev, S. (2017) A Deep Learning Approach to Diabetic Blood Glucose Prediction. Frontiers in Applied Mathematics and Statistics, 3, Article No. 14. [Google Scholar] [CrossRef] 
[49] Zhu, T., Li, K., Chen, J., et al. (2020) Dilated Recurrent Neural Networks for Glucose Forecasting in Type 1 Diabetes. Journal of Healthcare Informatics Research, 4, 308-324. [Google Scholar] [CrossRef] [PubMed]
[50] Li, K., Daniels, J., Liu, C., et al. (2020) Convolutional Recurrent Neural Networks for Glucose Prediction. IEEE Journal of Biomedical and Health Informatics, 24, 603-613. [Google Scholar] [CrossRef] 

为你推荐