Data-Driven Robust Control for Type 1 Diabetes Under Meal and Exercise Uncertainties

  • Nicola Paoletti
  • Kin Sum Liu
  • Scott A. Smolka
  • Shan Lin
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10545)


We present a fully closed-loop design for an artificial pancreas (AP) which regulates the delivery of insulin for the control of Type I diabetes. Our AP controller operates in a fully automated fashion, without requiring any manual interaction (e.g. in the form of meal announcements) with the patient. A major obstacle to achieving closed-loop insulin control is the uncertainty in those aspects of a patient’s daily behavior that significantly affect blood glucose, especially in relation to meals and physical activity. To handle such uncertainties, we develop a data-driven robust model-predictive control framework, where we capture a wide range of individual meal and exercise patterns using uncertainty sets learned from historical data. These sets are then used in the controller and state estimator to achieve automated, precise, and personalized insulin therapy. We provide an extensive in silico evaluation of our robust AP design, demonstrating the potential of this approach, without explicit meal announcements, to support high carbohydrate disturbances and to regulate glucose levels in large clusters of virtual patients learned from population-wide survey data.



Research supported in part by AFOSR Grant FA9550-14-1-0261 and NSF Grants IIS-1447549, CNS-1446832, CNS-1445770, CNS-1445770, CNS-1553273, CNS-1536086, and IIS-1460370.


  1. 1.
    Bertsimas, D., Gupta, V., Kallus, N.: Data-driven robust optimization. arXiv preprint arXiv:1401.0212 (2013)
  2. 2.
    Centers for Disease Control and Prevention. National Diabetes Statistics Report: Estimates of Diabetes and its Burden in the United States. US Department of Health and Human Services, Atlanta (2014)Google Scholar
  3. 3.
    Dassau, E., Bequette, B.W., Buckingham, B.A., Doyle, F.J.: Detection of a meal using continuous glucose monitoring. Diab. Care 31(2), 295–300 (2008)CrossRefGoogle Scholar
  4. 4.
    De Nicolao, G., Magni, L., Dalla Man, C., Cobelli, C.: Modeling and control of diabetes: towards the artificial pancreas. IFAC Proc. Vols. 44(1), 7092–7101 (2011)CrossRefGoogle Scholar
  5. 5.
    Efron, B., Tibshirani, R.J.: An Introduction to the Bootstrap. CRC Press, Boca Raton (1994)zbMATHGoogle Scholar
  6. 6.
    Gondhalekar, R., Dassau, E., Doyle, F.J.: Moving-horizon-like state estimation via continuous glucose monitor feedback in MPC of an artificial pancreas for type 1 diabetes. In: 2014 IEEE 53rd Annual Conference on Decision and Control (CDC), pp. 310–315. IEEE (2014)Google Scholar
  7. 7.
    Gondhalekar, R., Dassau, E., Doyle, F.J.: Periodic zone-MPC with asymmetric costs for outpatient-ready safety of an artificial pancreas to treat type 1 diabetes. Automatica 71, 237–246 (2016)MathSciNetCrossRefzbMATHGoogle Scholar
  8. 8.
    Haseltine, E.L., Rawlings, J.B.: Critical evaluation of extended Kalman filtering and moving-horizon estimation. Ind. Eng. Chem. Res. 44(8), 2451–2460 (2005)CrossRefGoogle Scholar
  9. 9.
    Hernandez-Ordonez, M., Campos-Delgado, D.: An extension to the compartmental model of type 1 diabetic patients to reproduce exercise periods with glycogen depletion and replenishment. J. Biomech. 41(4), 744–752 (2008)CrossRefGoogle Scholar
  10. 10.
    Hovorka, R.: Closed-loop insulin delivery: from bench to clinical practice. Nat. Rev. Endocrinol. 7(7), 385–395 (2011)CrossRefGoogle Scholar
  11. 11.
    Hovorka, R., et al.: Nonlinear model predictive control of glucose concentration in subjects with type 1 diabetes. Physiol. Meas. 25(4), 905 (2004)CrossRefGoogle Scholar
  12. 12.
    Huyett, L.M., Dassau, E., Zisser, H.C., Doyle III, F.J.: Design and evaluation of a robust PID controller for a fully implantable artificial pancreas. Ind. Eng. Chem. Res. 54(42), 10311–10321 (2015)CrossRefGoogle Scholar
  13. 13.
    Jacobs, P.G., et al.: Incorporating an exercise detection, grading, and hormone dosing algorithm into the artificial pancreas using accelerometry and heart rate. J. Diab. Sci. Technol., 1932296815609371 (2015)Google Scholar
  14. 14.
    Kienitz, K.H., Yoneyama, T.: A robust controller for insulin pumps based on H-infinity theory. IEEE Trans. Biomed. Eng. 40(11), 1133–1137 (1993)CrossRefGoogle Scholar
  15. 15.
    Kovács, L., Benyó, B., Bokor, J., Benyó, Z.: Induced L2-norm minimization of glucose-insulin system for Type I diabetic patients. Comput. Methods Programs Biomed. 102(2), 105–118 (2011)CrossRefGoogle Scholar
  16. 16.
    Kovács, L., Szalay, P., Almássy, Z., Barkai, L.: Applicability results of a nonlinear model-based robust blood glucose control algorithm. J. Diab. Sci. Technol. 7(3), 708–716 (2013)CrossRefGoogle Scholar
  17. 17.
    Kovatchev, B., et al.: Feasibility of long-term closed-loop control: a multicenter 6-month trial of 24/7 automated insulin delivery. Diab. Technol. Ther. (2017)Google Scholar
  18. 18.
    Laxminarayan, S., Reifman, J., Steil, G.M.: Use of a food and drug administration-approved type 1 diabetes mellitus simulator to evaluate and optimize a proportional-integral-derivative controller. J. Diab. Sci. Technol. 6(6), 1401–1412 (2012)CrossRefGoogle Scholar
  19. 19.
    Lee, H., Buckingham, B.A., Wilson, D.M., Bequette, B.W.: A closed-loop artificial pancreas using model predictive control and a sliding meal size estimator. J. Diab. Sci. Technol. 3(5), 1082–1090 (2009)CrossRefGoogle Scholar
  20. 20.
    Lee, J.J., Gondhalekar, R., Doyle, F.J.: Design of an artificial pancreas using zone model predictive control with a moving horizon state estimator. In: 2014 IEEE 53rd Annual Conference on Decision and Control (CDC), pp. 6975–6980. IEEE (2014)Google Scholar
  21. 21.
    Lenart, P.J., Parker, R.S.: Modeling exercise effects in type i diabetic patients. IFAC Proc. Vols. 35(1), 247–252 (2002)CrossRefGoogle Scholar
  22. 22.
    Ly, T.T., et al.: Day and night closed-loop control using the integrated Medtronic hybrid closed-loop system in type 1 diabetes at diabetes camp. Diab. Care 38(7), 1205–1211 (2015)CrossRefGoogle Scholar
  23. 23.
    Magni, L., et al.: Model predictive control of glucose concentration in type I diabetic patients: an in silico trial. Biomed. Signal Process. Control 4(4), 338–346 (2009)CrossRefGoogle Scholar
  24. 24.
    Paoletti, N., Liu, K.S., Smolka, S.A., Lin, S.: Data-driven robust control for type 1 diabetes under meal and exercise uncertainties. CoRR, 1707.02246 (2017)Google Scholar
  25. 25.
    Parker, R.S., Doyle, F.J., Ward, J.H., Peppas, N.A.: Robust H\(_\infty \) glucose control in diabetes using a physiological model. AIChE J. 46(12), 2537–2549 (2000)CrossRefGoogle Scholar
  26. 26.
    Perea, L., How, J., Breger, L., Elosegui, P.: Nonlinearity in sensor fusion: divergence issues in EKF, modified truncated GSF, and UKF. In: AIAA Guidance, Navigation and Control Conference and Exhibit, p. 6514 (2007)Google Scholar
  27. 27.
    Rao, C.V., Rawlings, J.B., Mayne, D.Q.: Constrained state estimation for nonlinear discrete-time systems: stability and moving horizon approximations. IEEE Trans. Autom. Control 48(2), 246–258 (2003)MathSciNetCrossRefzbMATHGoogle Scholar
  28. 28.
    Resalat, N., El Youssef, J., Reddy, R., Jacobs, P.G.: Design of a dual-hormone model predictive control for artificial pancreas with exercise model. In: 2016 IEEE 38th Annual International Conference of the Engineering in Medicine and Biology Society (EMBC), pp. 2270–2273. IEEE (2016)Google Scholar
  29. 29.
    Ruiz-Velázquez, E., Femat, R., Campos-Delgado, D.: Blood glucose control for type I diabetes mellitus: a robust tracking H\(_\infty \) problem. Control Eng. Pract. 12(9), 1179–1195 (2004)CrossRefGoogle Scholar
  30. 30.
    Stoorvogel, A.A.: The H\(_\infty \) Control Problem: A State Space Approach. Prentice Hall, Upper Saddle River (1992)zbMATHGoogle Scholar
  31. 31.
    Szalay, P., Eigner, G., Kovács, L.A.: Linear matrix inequality-based robust controller design for type-1 diabetes model. IFAC Proc. Vols. 47(3), 9247–9252 (2014)CrossRefGoogle Scholar
  32. 32.
    Van Der Merwe, R.: Sigma-point Kalman filters for probabilistic inference in dynamic state-space models. Ph.D. thesis, Oregon Health & Science University (2004)Google Scholar
  33. 33.
    Wang, Y., Zisser, H., Dassau, E., Jovanovič, L., Doyle, F.J.: Model predictive control with learning-type set-point: Application to artificial pancreatic \(\beta \)-cell. AIChE J. 56(6), 1510–1518 (2010)CrossRefGoogle Scholar
  34. 34.
    Weimer, J., Chen, S., Peleckis, A., Rickels, M.R., Lee, I.: Physiology-invariant meal detection for type 1 diabetes. Diab. Technol. Ther. 18(10), 616–624 (2016)CrossRefGoogle Scholar
  35. 35.
    Welch, G., Bishop, G.: An Introduction to the Kalman Filter. Technical report, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA (1995)Google Scholar
  36. 36.
    Wilinska, M.E., et al.: Insulin kinetics in type-1 diabetes: continuous and bolus delivery of rapid acting insulin. IEEE Trans. Biomed. Eng. 52(1), 3–12 (2005)CrossRefGoogle Scholar
  37. 37.
    Wilinska, M.E., et al.: Simulation environment to evaluate closed-loop insulin delivery systems in type 1 diabetes. J. Diab. Sci. Technol. 4(1), 132–144 (2010)CrossRefGoogle Scholar
  38. 38.
    Zavitsanou, S., Chakrabarty, A., Dassau, E., Doyle, F.J.: Embedded control in wearable medical devices: application to the artificial pancreas. Processes 4(4), 35 (2016)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Nicola Paoletti
    • 1
  • Kin Sum Liu
    • 1
  • Scott A. Smolka
    • 1
  • Shan Lin
    • 2
  1. 1.Department of Computer ScienceStony Brook UniversityStony BrookUSA
  2. 2.Department of Electrical and Computer EngineeringStony Brook UniversityStony BrookUSA

Personalised recommendations