Skip to main content
SpringerLink
Log in

A 2-dimensional model framework for blood glucose prediction based on iterative learning control architecture

  • Original Article
  • Published:
Medical & Biological Engineering & Computing Aims and scope Submit manuscript

Abstract

The accurate, timely, and personalized prediction for future blood glucose (BG) levels is undoubtedly needed for further advancement of diabetes management technologies. Human inherent circadian rhythm and regular lifestyle resulting in similarity of daily glycemic dynamics play a positive role in the prediction of blood glucose. Inspired by the iterative learning control (ILC) method in the field of automatic control, a 2-dimensional (2-D) model framework is constructed to predict the future blood glucose levels by taking both the short-range information within a day (intra-day) and long-range information between days (inter-day) into account. In this framework, the radial basis function neural network was applied to capture nonlinear relationships in glycemic metabolism, that is, short-range temporal dependence and long-range contemporaneous dependence on previous days. We build models for each patient, and the models were tested on the in silico datasets at various prediction horizons (PHs). The learning model developed in the 2-D framework successfully increases the accuracy and reduces the delay of predictions. This modeling framework provides a new point of view for BG level prediction and contributes to the development of personalized glucose management, such as hypoglycemia warning and glycemic control.

Graphical abstract

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

References

  1. American Diabetes Association Professional Practice Committee (2022) 7. Diabetes technology: standards of medical care in diabetes-2022. Diabetes Care 45:S97–S112. https://doi.org/10.2337/dc22-S007

    Article  Google Scholar 

  2. Diabetes Control and Complications Trial Research Group, Nathan DM, Genuth S et al (1993) The effect of intensive treatment of diabetes on the development and progression of long-term complications in insulin-dependent diabetes mellitus. N Engl J Med 329:977–986. https://doi.org/10.1056/NEJM199309303291401

    Article  Google Scholar 

  3. Boughton CK, Hovorka R (2019) Is an artificial pancreas (closed-loop system) for type 1 diabetes effective? Diabet Med J Br Diabet Assoc 36:279–286. https://doi.org/10.1111/dme.13816

    Article  CAS  Google Scholar 

  4. American Diabetes Association Professional Practice Committee (2022) 6. Glycemic targets: standards of medical care in diabetes-2022. Diabetes Care 45:S83–S96. https://doi.org/10.2337/dc22-S006

    Article  Google Scholar 

  5. Cobelli C, Renard E, Kovatchev B (2011) Artificial pancreas: past, present, future. Diabetes 60:2672–2682. https://doi.org/10.2337/db11-0654

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  6. Nimri R, Kovatchev B, Phillip M (2021) Decision support systems and closed-loop. Diabetes Technol Ther 23:S69–S84. https://doi.org/10.1089/dia.2021.2505

    Article  PubMed  Google Scholar 

  7. Xie F, Chan JC, Ma RC (2018) Precision medicine in diabetes prevention, classification and management. J Diabetes Investig 9:998–1015. https://doi.org/10.1111/jdi.12830

    Article  PubMed  PubMed Central  Google Scholar 

  8. Doyle FJ, Huyett LM, Lee JB et al (2014) Closed-loop artificial pancreas systems: engineering the algorithms. Diabetes Care 37:1191–1197. https://doi.org/10.2337/dc13-2108

    Article  PubMed  PubMed Central  Google Scholar 

  9. Woldaregay AZ, Årsand E, Botsis T et al (2019) Data-driven blood glucose pattern classification and anomalies detection: machine-learning applications in type 1 diabetes. J Med Internet Res 21:e11030. https://doi.org/10.2196/11030

    Article  PubMed  PubMed Central  Google Scholar 

  10. Oviedo S, Vehí J, Calm R, Armengol J (2017) A review of personalized blood glucose prediction strategies for T1DM patients. Int J Numer Methods Biomed Eng 33:e2833. https://doi.org/10.1002/cnm.2833

    Article  Google Scholar 

  11. Zhu T, Li K, Herrero P, Georgiou P (2023) Personalized blood glucose prediction for type 1 diabetes using evidential deep learning and meta-learning. IEEE Trans Biomed Eng 70:193–204. https://doi.org/10.1109/TBME.2022.3187703

    Article  PubMed  Google Scholar 

  12. Yang G, Liu S, Li Y, He L (2023) Short-term prediction method of blood glucose based on temporal multi-head attention mechanism for diabetic patients. Biomed Signal Process Control 82:104552. https://doi.org/10.1016/j.bspc.2022.104552

    Article  Google Scholar 

  13. Khadem H, Nemat H, Elliott J, Benaissa M (2023) Blood glucose level time series forecasting: nested deep ensemble learning lag fusion. Bioeng Basel Switz 10:487. https://doi.org/10.3390/bioengineering10040487

    Article  CAS  Google Scholar 

  14. Arora S, Kumar S, Kumar P (2022) Multivariate models of blood glucose prediction in type1 diabetes: a survey of the state-of-the- art. Curr Pharm Biotechnol. https://doi.org/10.2174/1389201023666220603092433

    Article  Google Scholar 

  15. Yang T, Yu X, Ma N et al (2022) An autonomous channel deep learning framework for blood glucose prediction. Appl Soft Comput 120:108636. https://doi.org/10.1016/j.asoc.2022.108636

    Article  Google Scholar 

  16. 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. Comput Methods Programs Biomed 196:105628. https://doi.org/10.1016/j.cmpb.2020.105628

    Article  PubMed  Google Scholar 

  17. Yang J, Li L, Shi Y, Xie X (2019) An ARIMA model with adaptive orders for predicting blood glucose concentrations and hypoglycemia. IEEE J Biomed Health Inform 23:1251–1260. https://doi.org/10.1109/JBHI.2018.2840690

    Article  PubMed  Google Scholar 

  18. Zecchin C, Facchinetti A, Sparacino G, Cobelli C (2016) How much is short-term glucose prediction in type 1 diabetes improved by adding insulin delivery and meal content information to CGM data? A proof-of-concept study. J Diabetes Sci Technol 10:1149–1160. https://doi.org/10.1177/1932296816654161

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  19. Zulj S, Carvalho P, Ribeiro RT et al (2021) Data size considerations and hyperparameter choices in case-based reasoning approach to glucose prediction. Biocybern Biomed Eng 41:733–745. https://doi.org/10.1016/j.bbe.2021.04.013

    Article  Google Scholar 

  20. Hamdi T, Ben Ali J, Di Costanzo V et al (2018) Accurate prediction of continuous blood glucose based on support vector regression and differential evolution algorithm. Biocybern Biomed Eng 38:362–372. https://doi.org/10.1016/j.bbe.2018.02.005

    Article  Google Scholar 

  21. Liberman A, Barnard-Kelly K (2023) Diabetes technology and the human factor. Diabetes Technol Ther 25:S-191. https://doi.org/10.1089/dia.2023.2512

    Article  Google Scholar 

  22. Ma N, Zhao Y, Wen S et al (2020) Online blood glucose prediction using auto-regressive moving average model with residual compensation network. In: Bach K, Bunescu RC, Marling C, Wiratunga N (eds) Proceedings of the 5th international workshop on knowledge discovery in healthcare data co-located with 24th Eu-ropean conference on artificial intelligence, KDH@ECAI 2020, Santiago de Compostela, Spain & Virtually, August 29-30, 2020. CEUR-WS.org, pp 151–155

  23. Sparacino G, Zanderigo F, Corazza S et al (2007) Glucose concentration can be predicted ahead in time from continuous glucose monitoring sensor time-series. IEEE Trans Biomed Eng 54:931–937. https://doi.org/10.1109/TBME.2006.889774

    Article  PubMed  Google Scholar 

  24. He J, He T, Wang Y (2019) Blood glucose concentration prediction based on canonical correlation analysis. In: 2019 Chinese Control Conference. pp 2942–2947. https://doi.org/10.23919/ChiCC.2019.8865767

  25. He J, Wang Y (2020) Blood glucose concentration prediction based on kernel canonical correlation analysis with particle swarm optimization and error compensation. Comput Methods Programs Biomed 196:105574. https://doi.org/10.1016/j.cmpb.2020.105574

    Article  PubMed  Google Scholar 

  26. Pérez-Gandía C, Facchinetti A, Sparacino G et al (2010) Artificial neural network algorithm for online glucose prediction from continuous glucose monitoring. Diabetes Technol Ther 12:81–88. https://doi.org/10.1089/dia.2009.0076

    Article  PubMed  Google Scholar 

  27. Allam F, Nossair Z, Gomma H et al (2011) Prediction of subcutaneous glucose concentration for type-1 diabetic patients using a feed forward neural network. In: The 2011 International Conference on Computer Engineering Systems. pp 129–133. https://doi.org/10.1109/ICCES.2011.6141026

  28. Hamdi T, Ben Ali J, Fnaiech N et al (2017) Artificial neural network for blood glucose level prediction. In: 2017 International Conference on Smart, Monitored and Controlled Cities. pp 91–95

  29. Ben Ali J, Hamdi T, Fnaiech N et al (2018) Continuous blood glucose level prediction of type 1 diabetes based on artificial neural network. Biocybern Biomed Eng 38:828–840. https://doi.org/10.1016/j.bbe.2018.06.005

    Article  Google Scholar 

  30. Martinsson J, Schliep A, Eliasson B et al (2018) Automatic blood glucose predic-tion with confidence using recurrent neural networks. In: Bach K, Bunescu RC, Farri O et al (eds) Proceedings of the 3rd international workshop on knowledge discovery in healthcare data co-located with the 27th international joint confer-ence on artificial intelligence and the 23rd european conference on artificial in-telligence (IJCAI-ECAI 2018), Stockholm, Schweden, July 13, 2018. CEUR-WS.org, pp 64–68

  31. Dong Y, Wen R, Li Z et al (2019) Clu-RNN: A new RNN based approach to dia-betic blood glucose prediction. In: 2019 IEEE 7th International Conference on Bioinformatics and Computational Biology, pp 50–55. https://doi.org/10.1109/SM2C.2017.8071825

  32. Koutny T, Mayo M (2022) Predicting glucose level with an adapted branch predictor. Comput Biol Med 145:105388. https://doi.org/10.1016/j.compbiomed.2022.105388

    Article  PubMed  Google Scholar 

  33. Nemat H, Khadem H, Eissa MR et al (2022) Blood glucose level prediction: advanced deep-ensemble learning approACH. IEEE J Biomed Health Inform 26:2758–2769. https://doi.org/10.1109/JBHI.2022.3144870

    Article  PubMed  Google Scholar 

  34. Seaman GVF, Engel R, Swank RL, Hissen W (1965) Circadian periodicity in some physicochemical parameters of circulating blood. Nature 207:833–835. https://doi.org/10.1038/207833a0

    Article  CAS  PubMed  Google Scholar 

  35. Hinshaw L, Dalla Man C, Nandy DK et al (2013) Diurnal pattern of insulin action in type 1 diabetes: implications for a closed-loop system. Diabetes 62:2223–2229. https://doi.org/10.2337/db12-1759

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  36. Van Cauter E, Polonsky KS, Scheen AJ (1997) Roles of circadian rhythmicity and sleep in human glucose regulation. Endocr Rev 18:716–738. https://doi.org/10.1210/edrv.18.5.0317

    Article  PubMed  Google Scholar 

  37. Contreras I, Quirós C, Giménez M et al (2016) Profiling intra-patient type I diabetes behaviors. Comput Methods Programs Biomed 136:131–141. https://doi.org/10.1016/j.cmpb.2016.08.022

    Article  PubMed  Google Scholar 

  38. Montaser E, Diez J-L, Rossetti P et al (2020) Seasonal local models for glucose prediction in type 1 diabetes. IEEE J Biomed Health Inform 24:2064–2072. https://doi.org/10.1109/JBHI.2019.2956704

    Article  PubMed  Google Scholar 

  39. Bristow DA, Tharayil M, Alleyne AG (2006) A survey of iterative learning control. IEEE Control Syst Mag 26:96–114. https://doi.org/10.1109/MCS.2006.1636313

    Article  Google Scholar 

  40. Rodbard D (2018) Glucose Variability: a review of clinical applications and research developments. Diabetes Technol Ther 20:S2-5. https://doi.org/10.1089/dia.2018.0092

    Article  Google Scholar 

  41. Man CD, Micheletto F, Lv D et al (2014) The UVA/PADOVA type 1 diabetes simulator: new featureS. J Diabetes Sci Technol 8:26–34. https://doi.org/10.1177/1932296813514502

    Article  PubMed  PubMed Central  Google Scholar 

  42. Visentin R, Dalla Man C, Kudva YC et al (2015) Circadian variability of insulin sensitivity: physiological input for in silico artificial pancreas. Diabetes Technol Ther 17:1–7. https://doi.org/10.1089/dia.2014.0192

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  43. Visentin R, Man CD, Cobelli C (2016) One-day Bayesian cloning of type 1 diabetes subjects: toward a single-day UVA/padova type 1 diabetes simulator. IEEE Trans Biomed Eng 63:2416–2424. https://doi.org/10.1109/TBME.2016.2535241

    Article  PubMed  Google Scholar 

  44. Visentin R, Dalla Man C, Kovatchev B, Cobelli C (2014) The university of Virginia/Padova type 1 diabetes simulator matches the glucose traces of a clinical trial. Diabetes Technol Ther 16:428–434. https://doi.org/10.1089/dia.2013.0377

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  45. Ahn H-S, Chen Y, Moore KL (2007) Iterative learning control: brief survey and categorization. IEEE Trans Syst Man Cybern Part C Appl Rev 37:1099–1121. https://doi.org/10.1109/TSMCC.2007.905759

    Article  Google Scholar 

  46. Bors A (2001) Introduction of the Radial Basis Function (RBF) Networks. In: Online Symposium for Electronics Engineers, pp 1–7

  47. Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks. J Mach Learn Res 9:249–256

    Google Scholar 

  48. Zecchin C, Facchinetti A, Sparacino G et al (2012) Neural network incorporating meal information improves accuracy of short-time prediction of glucose concentration. IEEE Trans Biomed Eng 59:1550–1560. https://doi.org/10.1109/TBME.2012.2188893

    Article  PubMed  Google Scholar 

  49. Rodbard D (2009) New and improved methods to characterize glycemic variability using continuous glucose monitoring. Diabetes Technol Ther 11:551–565. https://doi.org/10.1089/dia.2009.0015

    Article  CAS  PubMed  Google Scholar 

Download references

Funding

This study was supported by Natural Science Foundation of China (No. 61973067). The data simulator is developed by the university of Virginia/Padova.

Author information

Authors and Affiliations

  1. College of Information Sciences and Engineering, Northeastern University, No. 11 St. 3, Wenhua Road, Heping District, Shenyang, 110819, People’s Republic of China

    Shuang Wen, Hongru Li & Rui Tao

Authors
  1. Shuang Wen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hongru Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Rui Tao
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hongru Li.

Ethics declarations

Competing interests

The authors declare no competing interests.

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.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wen, S., Li, H. & Tao, R. A 2-dimensional model framework for blood glucose prediction based on iterative learning control architecture. Med Biol Eng Comput 61, 2593–2606 (2023). https://doi.org/10.1007/s11517-023-02866-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11517-023-02866-3

Keywords

Search

Navigation