Neural Adaptive Control of an Artificial Pancreas for People with Type 1 Diabetes Under Saturated Insulin Injection Rate

Subject Areas : Control systems

Sadegh Rezaei ¹ , Mohsen Parsa ²

1 - Department of Electrical Engineering- Najafabad Branch, Islamic Azad University, Najafabad, Iran
2 - Digital Processing and Machine Vision Research Center- Najafabad Branch, Islamic Azad University, Najafabad, Iran

Received: 2021-11-10 Accepted : 2022-01-22 Published : 2024-02-20

Keywords: Artificial Pancreas, Bergman model, adaptive neural network control, asymmetric actuator saturation,

Abstract :

It is essential to control vital variables in patients whose natural control system has been compromised for some reason. One of these vital variables is blood glucose levels. Unfortunately, in people with diabetes (blood sugar), blood glucose levels are not regulated properly. To compensate for this lack, in recent years, several studies and efforts have been made to build and improve the function of the artificial pancreas to control blood sugar. The presence of factors such as multiple uncertainties due to physiological differences in individuals, various activities during the day, delayed effects of carbohydrates on blood sugar levels, stress and exercise make controlling the artificial pancreas a challenging system. But one of the most important challenges in this area, which has not been less addressed in the literature is the limitation on the allowable dose of insulin injected into the artificial pancreas for patients with type 1 diabetes. On the one hand, injecting a high dose of insulin can cause problems such as hyperglycemia issues and on the other hand, injecting a negative dose of insulin is meaningless. In this paper, after selecting the Bergman model and considering the existence of asymmetric saturation in the actuator, the back-stepping control method is used and it is combined with an adaptive technique to improve the controller performance. Finally, simulation results depict that in the presence of large step disturbance, the insulation rate remains in the allowed band of zero to 20 mU/min, and the blood glucose level does not exceed the appropriate level 130mg/dl.

References:

[1] C. Bommer, V. Sagalova, E. Heesemann, J. Manne-Goehler, R. Atun, T. Barnighausen, J. Davies, S. Vollmer, “Global economic burden of diabetes in adults: Projections from 2015 to 2030”, American Diabetes Association, vol. 41, no. 5, pp. 963-970, May 2018 (doi: 10.2337/dc17-1962).

[2] A.D. Association, “Economic costs of diabetes in the US in 2012, diabetes care”, Diabetes Care, vol. 36, no. 4, pp. 1033-1046, Apr. 2013 (doi: 10.2337/dc12-2625).

[3] M. Bouquot, S. Gaujoux S, F. Cauchy, D. Birnbaum, S. Dokmak, P. Levy, O. Soubrane, A. Sauvanet, “Pancreatectomy for pancreatic  incidentaloma: what are the risk?”, Journal Pancreatology, vol. 18, no. 1, pp. 114-121, Jan. 2018 (doi: 10.1016/j.pan.2017.11.002).

[4] M.A. Marini, S. Frontoni, E. Succurro, F. Arturi, A. Sciacqua, M.L. Hribal, F. Perticone, G. Sesti, “Insulin sensitivity, and β-cell function in relation to hemoglobin A1C”, Nutrition, Metabolism and Cardiovascular Diseases, vol. 24, no. 1, pp. 27-33, Jan. 2014 (doi: 10.1016/j.numecd.2013.01.011).

[5] A.D. Association, “Standards of medical care in diabetesd,” Diabetes Care, vol. 37, no. 1, pp. 14-80, Jan. 2014 (doi: 10.2337/dc14-S014).

[6] D. Elleri, D. B. Dunger, R. Hovorka, “Closed-loop insulin delivery for treatment of type 1 diabetes”, BMC Medicine, vol. 9, no. 120, Nov. 2011 (doi: 10.1186/1741-7015-9-120).

[7] N. Resalat, J.E. Youssef, R. Reddy, P.G. Jacobs, “Design of a dual-hormone model predictive control for artificial pancreas with exercise model”, Proceeding of the IEEE/EMBC, pp. 2270-2273, Orlando, FL, Aug. 2016 (doi:10.1109/EMBC.2016.7591182).

[8] D. Boiroux, V. Batora, M. Hagdrup, S.L. Wendt, N.K. Poulsen, H. Madsen, J.B. Jorgensen, “Adaptive model predictive control for a dual-hormone artificial pancreas”, Journal of Process Control, vol. 68, pp. 105-117, Aug. 2018 (doi: 10.1016/j.jprocont.2018.05.003).

[9] D. Wexler, J. Meigs, E. Cagliero, D. Nathan, R. Grant, “Prevalence of hyper- and hypoglycemia among inpatients with diabetes”, Diabetes Care, vol. 30, no. 2, pp. 367-369, Feb. 2007 (doi: 10.2337/dc06-1715).

[10] S. Asadi, V. Nekoukar, “Adaptive fuzzy integral sliding mode control of blood glucose level in patients with type 1 diabetes: in silico Studies”, Mathematical Biosciences, Article Number: 30201283, Sept. 2018 (doi: 10.1016/j.mbs.2018.09.006).

[11] Y. Wei, P. W. Tse, Z. Yao, Y. Wang, “Adaptive backstepping output feedback control for a class of nonlinear fractional order systems”, Nonlinear Dynamics, vol. 86, no. 2, pp. 1047-1056, July 2016 (doi: 10.1007/s11071-016-2945-4).

[12] A. Nath, R. Dey, “Robust observer based control for plasma glucose regulation in type 1 diabetes patient using attractive ellipsoid method”, IET Systems Biology, vol. 13, no. 2, pp. 84-91, Apr. 2019 (doi: 10.1­049­/ie­t-syb.2018.5054).

[13] N. Doye, I. Vosh, H. Darouach, M. Schneider, “Static output feedback H∞ control for a fractional-order glucose-insulin system”, International Journal of Control, Automation and Systems, vol. 13, no. 4, pp. 798-807, May 2015 (doi.org/10.1007/s12555-013-9192-y).

[14] B. Farahmand, N. Vafamand, M. Dehghani, “Fuzzy model-based controller for blood glucose control in type 1 diabetes: An LMI approach”, Biomedical Signal Processing and Control, vol. 54, Article Number: 101627, Sept. 2019 (doi.org/10.1016/j.bspc.2019.101627).

[15] L. Chen, H. Mo, F. Wang, “Analysis and control of blood glucose situation for diabetic patients based on interval type-2 fuzzy sets”, International Journal of Fuzzy Systems, vol. 23, no. 4, pp. 1179-1193, Jun 2020 (doi: 10.1007/s40815-020-00918-6).

[16] S.K. Faruque, R. Padhi, “Optimal blood glucose regulation of diabetic patients using single network adaptive critics”, Optimal control application and methodes, vol. 32, no. 2, pp. 196-214, Apr. 2009 (doi: 10.1­109/CCA.2009.5281091).

[17] M. Goharimanesh, A. Lashkaripour, A. Abouei, “Fractional order PID controller for diabetes patients”, Journal of Computational Applied Mechanics, vol. 46, no. 1, pp. 69-76, Jan. 2015 (doi: 10.22059/JCAMEC­H.20­15­.53395).

[18] G. Marchetti, M. Barolo, L. Jovanovicy, H. Zissery, E. Seborg, “An improved PID switching control strategy for type 1 diabetes”, IEEE Trans. on Biomedical Engineering, vol. 55, no. 3, pp. 857-865, Feb.  2008 (doi: 10.1109/TBME.2008.915665).

[19] N. Anirudh, D. Dipankar, D. Rajeeb, “Robust observer-based adaptive control of blood glucose in diabetic patients”, International Journal of Control, vol. 94, no. 11, pp. 3054-3067, Apr. 2020 (doi: 10.1080/00207­17­9.2­020.1750705).

[20] Z. Kouchaki, M.R. Yousefi, K. Shojaee, “Blood glucose control for type 1 diabetic patients: robust fuzzy adaptive approach”, Journal of Intelligent Procedures in Electrical Technology, vol. 14, no. 53, pp. 31-48, June 2023 (in Persian).

[21] S. Nasr,  H. Mahmoodian, “Insulin drug regulation by general type 2 fuzzy controller with alpha plane”, Journal of Intelligent Procedures in Electrical Technology, vol. 10, no. 37, pp. 39-48, March 2019 (dor: 20.1001.1.23223871.1398.10.37.4.8) (in Persian).

[22] Y. Li, S. Tong, T. Li, “Adaptive fuzzy output-feedback control for output constrained nonlinear systems in the presence of input saturation”, Fuzzy Sets and Systems, vol. 248, pp. 138-155, Aug. 2014 (doi: 10.101­6/j.­fss.2013.11.006).