Abstract
Successful self-management of diabetes requires Continuous Glucose Monitors (CGMs). These CGMs have several limitations such as being invasive, expensive and limited in terms of use. Many techniques, in vain, have been proposed to overcome these limitations. Nowadays, with the help of the Internet of Medical Things (IoMT) technologies, researchers are working to find alternative solutions. They succeed to predict hypoglycemia and hyperglycemia peaks using Electrocardiogram (ECG) signals. However, they failed to use it to estimate the Blood Glucose Concentration (BGC) directly and in real time. Three patients with 08 days of measurements from the D1namo dataset contributed to the study. A new technique has been proposed to estimate the BGC curves based on ECG signals. We used a convolutional neural network to segment the different regions of ECG signals as well as we extracted ECG features that were required for the next step. Then, five regression models have been employed to estimate BGC using as input sixth ECG parameters. We were able to segment the ECG signals with an accuracy of 94% using the convolutional neural network algorithm. The best performance among all simulated models was provided by Exponential Gaussian Process Regression (GPR) with Root Mean Squared Error (RMSE) values of 0.32, 0.41, 0.67 and R-squared (R2) values of 98%, 80%, and 70% for patients 01, 02 and 03 respectively. The method indicates the potential use of ECG wearable devices as non-invasive for continuous blood glucose monitoring, which is affordable and durable.
Similar content being viewed by others
Data availability statement
This work used the D1NAMO dataset acquired from human participants in a previous study. The dataset is open source and available at https://zenodo.org/record/1421616.
References
Vishnu S, Ramson SRJ, Jegan R (2020) Internet of Medical Things (IoMT) - An overview. In: 2020 5th International Conference on Devices, Circuits and Systems (ICDCS). IEEE, Coimbatore, India, pp 101–104
Ometov A, Shubina V, Klus L et al (2021) A survey on wearable technology history state-of-the-art and current challenges. Comput Netw. https://doi.org/10.1016/j.comnet.2021.108074
Fellah Arbi K, Soulimane S, Saffih F (2020) IoT technologies combining glucose control with physiological signal: comparative study. In: 2020 International Conference on Electrical Engineering (ICEE). IEEE, Istanbul, Turkey, pp 1–6
Gusev M, Poposka L, Spasevski G et al (2020) Noninvasive glucose measurement using machine learning and neural network methods and correlation with heart rate variability. J Sens 2020:1–13. https://doi.org/10.1155/2020/9628281
Paschou SA, Papadopoulou-Marketou N, Chrousos GP, Kanaka-Gantenbein C (2018) On type 1 diabetes mellitus pathogenesis. Endocr Connect 7:R38–R46. https://doi.org/10.1530/EC-17-0347
Diabetes Control and Complications Trial/Epidemiology of Diabetes Interventions and Complications (DCCT/EDIC) Study Research Group (2005) Intensive Diabetes Treatment and Cardiovascular Disease in Patients with Type 1 Diabetes. N Engl J Med 353(25):2643–2653
Freeman, R. (2007). Hypoglycemia and the Autonomic Nervous System. In: Veves, A., Malik, R.A. (eds) Diabetic Neuropathy. Clinical Diabetes. Humana Press. https://doi.org/10.1007/978-1-59745-311-0_23
Seshadri DR, Bittel B, Browsky D et al (2020) Accuracy of Apple Watch for Detection of Atrial Fibrillation. Circulation 141:702–703. https://doi.org/10.1161/CIRCULATIONAHA.119.044126
Bayoumy K, Gaber M, Elshafeey A et al (2021) Smart wearable devices in cardiovascular care: where we are and how to move forward. Nat Rev Cardiol 18:581–599. https://doi.org/10.1038/s41569-021-00522-7
Lipponen JA, Kemppainen J, Karjalainen PA et al (2011) Hypoglycemia detection based on cardiac repolarization features. 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE, Boston, MA, pp 4697–4700
Alexakis C, Nyongesa HO, Saatchi R et al (2003) Feature extraction and classification of electrocardiogram (ECG) signals related to hypoglycaemia. Computers in Cardiology, 2003. IEEE, Thessaloniki Chalkidiki, Greece, pp 537–540
D’Imperio S, Monasky MM, Micaglio E et al (2021) Early morning QT prolongation during hypoglycemia: only a matter of glucose? Front Cardiovasc Med. https://doi.org/10.3389/fcvm.2021.688875
Murphy NP, Ford-Adams ME, Ong KK et al (2004) Prolonged cardiac repolarisation during spontaneous nocturnal hypoglycaemia in children and adolescents with type 1 diabetes. Diabetologia 47:1940–1947. https://doi.org/10.1007/s00125-004-1552-y
Lee SP, Yeoh L, Harris ND et al (2004) Influence of Autonomic neuropathy on QTc interval lengthening during hypoglycemia in type 1 diabetes. Diabetes 53:1535–1542. https://doi.org/10.2337/diabetes.53.6.1535
Elvebakk O, Tronstad C, Birkeland KI et al (2019) A multiparameter model for non-invasive detection of hypoglycemia. Physiol Meas. https://doi.org/10.1088/1361-6579/ab3676
Laitinen T, Lyyra-Laitinen T, Huopio H et al (2008) Electrocardiographic alterations during hyperinsulinemic hypoglycemia in healthy subjects: ECG changes during hypoglycemia. Ann Noninvasive Electrocardiol 13:97–105. https://doi.org/10.1111/j.1542-474X.2008.00208.x
Nguyen LL, Su S, Nguyen HT (2012) Identification of Hypoglycemia and Hyperglycemia in Type 1 Diabetic patients using ECG parameters. 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE, San Diego, CA, pp 2716–2719
Porumb M, Stranges S, Pescapè A, Pecchia L (2020) Precision medicine and artificial intelligence: a pilot study on deep learning for hypoglycemic events detection based on ECG. Sci Rep 10:170. https://doi.org/10.1038/s41598-019-56927-5
Nguyen HT, Ghevondian N, Jones TW. Neural-network detection of hypoglycemic episodes in children with type 1 diabetes using physiological parameters. Conf Proc IEEE Eng Med Biol Soc. 2006;2006:6053-6. https://doi.org/10.1109/IEMBS.2006.259482. PMID: 17945929
Howsmon D, Bequette BW (2015) Hypo- and hyperglycemic alarms: devices and algorithms. J Diabetes Sci Technol 9:1126–1137. https://doi.org/10.1177/1932296815583507
Cordeiro R, Karimian N, Park Y (2021) Hyperglycemia identification using ECG in deep learning era. Sensors 21:6263. https://doi.org/10.3390/s21186263
Olde Bekkink M, Koeneman M, de Galan BE, Bredie SJ (2019) Early detection of hypoglycemia in type 1 diabetes using heart rate variability measured by a wearable device. Diabetes Care 42:689–692. https://doi.org/10.2337/dc18-1843
Nuryani N, Ling SSH, Nguyen HT (2012) Electrocardiographic signals and swarm-based support vector machine for hypoglycemia detection. Ann Biomed Eng 40:934–945. https://doi.org/10.1007/s10439-011-0446-7
San PP, Ling SH, Nguyen HT (2016) Deep learning framework for detection of hypoglycemic episodes in children with type 1 diabetes. 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). IEEE, Orlando, FL, USA, pp 3503–3506
Laguna, Pablo, Roger G. Mark, AL et al (1997) A database for evaluation of algorithms for measurement of QT and other waveform intervals in the ECG. Computers in Cardiology. Vol 24 pp 673–676
Dubosson F, Ranvier J-E, Bromuri S et al (2018) The open D1NAMO dataset: a multi-modal dataset for research on non-invasive type 1 diabetes management. Inform Med Unlocked 13:92–100. https://doi.org/10.1016/j.imu.2018.09.003
Luna BA, Batchvarov VN, Malik M (2006) The morphology of the electrocardiogram. In: Camm AJ, Luscher TF, Serruys PW, editors. ESC Textbook of Cardiovascular Medicine. 1st ed. Oxford: Black well Publishing; p 1–36
Arakawa T, Tomoto K, Nitta H et al (2020) A Wearable cellulose acetate-coated mouthguard biosensor for in vivo salivary glucose measurement. Anal Chem 92:12201–12207. https://doi.org/10.1021/acs.analchem.0c01201
Kim S, Jeon H-J, Park S et al (2020) Tear glucose measurement by reflectance spectrum of a nanoparticle embedded contact lens. Sci Rep 10:8254. https://doi.org/10.1038/s41598-020-65103-z
Das S, Pal M (2020) Review—non-invasive monitoring of human health by exhaled breath analysis: a comprehensive review. J Electrochem Soc. https://doi.org/10.1149/1945-7111/ab67a6
Xue Y, Thalmayer AS, Zeising S et al (2022) Commercial and scientific solutions for blood glucose monitoring—a review. Sensors 22:425. https://doi.org/10.3390/s22020425
Lee I, Probst D, Klonoff D, Sode K (2021) Continuous glucose monitoring systems - current status and future perspectives of the flagship technologies in biosensor research -. Biosens Bioelectron. https://doi.org/10.1016/j.bios.2021.113054
Acknowledgements
The authors would like to thank the Scientific Research and Technological Development Centre for the financial assistance through monthly allowances provided to doctoral students to conduct their research
Funding
No funding was received for conducting this study. It is an academic Ph.D. study.
Author information
Authors and Affiliations
Contributions
All authors were involved in the work leading up to the manuscript. The results are appropriately placed in the context of prior and existing research. All sources used are properly disclosed (correct citation).
Corresponding author
Ethics declarations
Conflict of interest
No conflict of interest.
Ethical approval
This work used the D1NAMO dataset acquired from human participants in a previous study. The dataset is open source and available at https://zenodo.org/record/1421616.
Informed consent
Not applicable
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Fellah Arbi, K., Soulimane, S., Saffih, F. et al. Blood glucose estimation based on ECG signal. Phys Eng Sci Med 46, 255–264 (2023). https://doi.org/10.1007/s13246-022-01214-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13246-022-01214-3