The use of reinforcement learning algorithms to meet the challenges of an artificial pancreas

References

• Pachler C, Plank J, Weinhandl H Tight glycaemic control by an automated algorithm with time-variant sampling in medical ICU patients. Intensive Care Med. 34(7), 1224–1230 (2008).
   PubMed Web of Science ®Google Scholar
• Elleri D, Allen JM, Biagioni M Evaluation of a portable ambulatory prototype for automated overnight closed-loop insulin delivery in young people with type 1 diabetes. Pediatr. Diab. 13(6), 449–453 (2012).
   PubMed Web of Science ®Google Scholar
• Atlas E, Nimri R, Miller S, Grunberg EA, Phillip M. MD-logic artificial pancreas system: a pilot study in adults with type 1 diabetes. Diab. Care 33(5), 1072–1076 (2010).
   PubMed Web of Science ®Google Scholar
• International Diabetes Federation. IDF Diabetes Atlas (5th edition). Brussels, Belgium (2011)
   Google Scholar
• Clemens AH, Chang PH, Myers RW. The development of Biostator, a Glucose Controlled Insulin Infusion System (GCIIS). Horm. Metab. Res. (Suppl. 7), 23–33 (1977).
   PubMedGoogle Scholar
• American Diabetes Association. Standards of medical care in diabetes – 2011. Diab. Care 34(Suppl. 1), S11–S61 (2011).
   PubMed Web of Science ®Google Scholar
• Vaddiraju S, Burgess DJ, Tomazos I, Jain FC, Papadimitrakopoulos F. Technologies for continuous glucose monitoring: current problems and future promises. J. Diab. Sci.Technol. 4(6), 1540–1562 (2010).
   PubMedGoogle Scholar
• Clinical and Laboratory Standards Institute. Performance Metrics for Continuous Intersitital Glucose Monitoring; Approved Guideline. Clinical and Laboratory Standards Institute document POCT05-A. Wayne: Clinical and Laboratory Standards Institute; (2008).
   Google Scholar
• Cengiz E, Tamborlane WV. A tale of two compartments: interstitial versus blood glucose monitoring. Diab. Technol. Ther. 11(Suppl. 1), S11–S16 (2009).
   PubMedGoogle Scholar
• Aussedat B, Dupire-Angel M, Gifford R, Klein JC, Wilson GS, Reach G. Interstitial glucose concentration and glycemia: implications for continuous subcutaneous glucose monitoring. Am. J. Physiol. Endocrinol. Metab. 278(4), E716–E728 (2000).
   Web of Science ®Google Scholar
• Lonnroth P, Jansson PA, Smith U. A microdialysis method allowing characterization of intercellular water space in humans. Am. J. Physiol. 253(2 Pt 1), E228–E231 (1987).
   PubMed Web of Science ®Google Scholar
• Rebrin K, Steil GM, van Antwerp WP, Mastrototaro JJ. Subcutaneous glucose predicts plasma glucose independent of insulin: implications for continuous monitoring. Am. J. Physiol. 277(3 Pt 1), E561–E571 (1999).
   PubMed Web of Science ®Google Scholar
• Baek YH, Jin HY, Lee KA The Correlation and accuracy of glucose levels between interstitial fluid and venous plasma by continuous glucose monitoring system. Korean Diab. J. 34(6), 350–358 (2010).
   PubMedGoogle Scholar
• Kulcu E, Tamada JA, Reach G, Potts RO, Lesho MJ. Physiological differences between interstitial glucose and blood glucose measured in human subjects. Diab. Care 26(8), 2405–2409 (2003).
   PubMed Web of Science ®Google Scholar
• Beier B, Musick K, Matsumoto A, Panitch A, Nauman E, Irazoqui P. Toward a continuous intravascular glucose monitoring system. Sensors 11(1), 409–424 (2011).
   PubMed Web of Science ®Google Scholar
• Skjaervold NK, Solligard E, Hjelme DR, Aadahl P. Continuous measurement of blood glucose: validation of a new intravascular sensor. Anesthesiology 114(1), 120–125 (2011).
   PubMed Web of Science ®Google Scholar
• Aye T, Block J, Buckingham B. Toward closing the loop: an update on insulin pumps and continuous glucose monitoring systems. Endocrinol. Metab. Clin. North America 39(3), 609–624 (2010).
   PubMed Web of Science ®Google Scholar
• Keenan DB, Mastrototaro JJ, Voskanyan G, Steil GM. Delays in minimally invasive continuous glucose monitoring devices: a review of current technology. J. Diab. Sci. Technol. 3(5), 1207–1214 (2009).
   PubMedGoogle Scholar
• Rebrin K, Sheppard NF Jr, Steil GM. Use of subcutaneous interstitial fluid glucose to estimate blood glucose: revisiting delay and sensor offset. J. Diab. Sci. Technol. 4(5), 1087–1098 (2010).
   PubMedGoogle Scholar
• Mastrototaro J. The MiniMed Continuous Glucose Monitoring System (CGMS). J. Pediatr. Endocrinol. Metab. 12(Suppl. 3), 751–758 (1999).
   PubMedGoogle Scholar
• Glucose Monitoring Study Group. Continuous glucose monitoring by means of the microdialysis technique: underlying fundamental aspects. Diab. Technol. Ther. 5(4), 545–561 (2003).
   PubMedGoogle Scholar
• Banting FG, Campbell WR, Fletcher AA. Further clinical experience with insulin (pancreatic extracts) in the treatment of diabetes mellitus. Br. Med. J. 1(3236), 8–12 (1923).
   PubMedGoogle Scholar
• Gilchrist JA, Best CH, Banting FG. Observations with insulin on department of soldiers’ civil Re-establishment diabetics. Canadian Med. Assoc. J. 13(8), 565–572 (1923).
   PubMedGoogle Scholar
• Renard E. Insulin delivery route for the artificial pancreas: subcutaneous, intraperitoneal, or intravenous? Pros and cons. J. Diab. Sci. Technol. 2(4), 735–738 (2008).
   PubMedGoogle Scholar
• Yasini S, Naghibi-Sistani MB, Karimpour A. Agent-based Simulation for Blood Glucose Control in Diabetic Patients. World Acad. Sci. Eng. Technol. 57(33), 11 (2009).
   Google Scholar
• McMahon GT, Arky RA. Inhaled insulin for diabetes mellitus. N. Engl. J. Med. 356(5), 497–502 (2007).
   PubMed Web of Science ®Google Scholar
• Farmer TG, Jr., Edgar TF, Peppas NA. The future of open- and closed-loop insulin delivery systems. J. Pharm. Pharmacol. 60(1), 1–13 (2008).
   PubMed Web of Science ®Google Scholar
• Kapitza C, Zijlstra E, Heinemann L, Castelli MC, Riley G, Heise T. Oral insulin: a comparison with subcutaneous regular human insulin in patients with type 2 diabetes. Diab. Care 33(6), 1288–1290 (2010).
   PubMed Web of Science ®Google Scholar
• Najafzadeh H, Kooshapur H, Kianidehkordi F. Evaluation of an oral insulin formulation in normal and diabetic rats. Indian J. Pharm. 44(1), 103–105 (2012).
   Google Scholar
• Diabetes Control and Complications Trial Research Group. The effect of intensive treatment of diabetes on the development and progression of long-term complications in insulin-dependent diabetes mellitus. The Diabetes Control and Complications Trial Research Group. N. Engl. J. Med. 329(14), 977–986 (1993).
   PubMed Web of Science ®Google Scholar
• Kumareswaran K, Evans ML, Hovorka R. Closed-loop insulin delivery: towards improved diabetes care. Discov. Med. 13(69), 159–170 (2012).
   PubMed Web of Science ®Google Scholar
• Thorens B. Brain glucose sensing and neural regulation of insulin and glucagon secretion. Diab. Obesity Metab. 13(Suppl. 1), 82–88 (2011).
   PubMed Web of Science ®Google Scholar
• Thorens B. Sensing of glucose in the brain. Handb. Exp. Pharmacol. (209), 277–294 (2012).
   Google Scholar
• Weinzimer SA, Steil GM, Swan KL, Dziura J, Kurtz N, Tamborlane WV. Fully automated closed-loop insulin delivery versus semiautomated hybrid control in pediatric patients with type 1 diabetes using an artificial pancreas. Diab. Care 31(5), 934–939 (2008).
   PubMed Web of Science ®Google Scholar
• Renard E, Place J, Cantwell M, Chevassus H, Palerm CC. Closed-loop insulin delivery using a subcutaneous glucose sensor and intraperitoneal insulin delivery: feasibility study testing a new model for the artificial pancreas. Diab. Care 33(1), 121–127 (2010).
   PubMed Web of Science ®Google Scholar
• Dassau E, Bequette BW, Buckingham BA, Doyle FJ 3rd. Detection of a meal using continuous glucose monitoring: implications for an artificial beta-cell. Diab. Care 31(2), 295–300 (2008).
   PubMed Web of Science ®Google Scholar
• Lee H, Buckingham BA, Wilson DM, Bequette BW. A closed-loop artificial pancreas using model predictive control and a sliding meal size estimator. J. Diab. Sci. Technol. 3(5), 1082–1090 (2009).
   PubMedGoogle Scholar
• Panteleon AE, Loutseiko M, Steil GM, Rebrin K. Evaluation of the effect of gain on the meal response of an automated closed-loop insulin delivery system. Diabetes 55(7), 1995–2000 (2006).
   PubMed Web of Science ®Google Scholar
• Steil GM, Palerm CC, Kurtz N The effect of insulin feedback on closed loop glucose control. J. Clin. Endocrinol. Metab. 96(5), 1402–1408 (2011).
   PubMed Web of Science ®Google Scholar
• Wintergerst KA, Deiss D, Buckingham B Glucose control in pediatric intensive care unit patients using an insulin-glucose algorithm. Diab. Technol. Ther. 9(3), 211–222 (2007).
   PubMed Web of Science ®Google Scholar
• Acikgoz US, Diwekar UM. Blood glucose regulation with stochastic optimal control for insulin-dependent diabetic patients. Chem. Eng. Sci. 65(3), 1227–1236 (2010).
   Web of Science ®Google Scholar
• Chee F, Savkin AV, Fernando TL, Nahavandi S. Optimal H infinity insulin injection control for blood glucose regulation in diabetic patients. IEEE Trans. Biomed. Eng. 52(10), 1625–1631 (2005).
   PubMed Web of Science ®Google Scholar
• Bruttomesso D, Farret A, Costa S Closed-loop artificial pancreas using subcutaneous glucose sensing and insulin delivery and a model predictive control algorithm: preliminary studies in Padova and Montpellier. J. Diab. Sci. Technol. 3(5), 1014–1021 (2009).
   PubMedGoogle Scholar
• Clarke WL, Anderson S, Breton M, Patek S, Kashmer L, Kovatchev B. Closed-loop artificial pancreas using subcutaneous glucose sensing and insulin delivery and a model predictive control algorithm: the Virginia experience. J. Diab. Sci. Technol. 3(5), 1031–1038 (2009).
   PubMedGoogle Scholar
• Elleri D, Allen JM, Nodale M Automated overnight closed-loop glucose control in young children with type 1 diabetes. Diab. Technol. Ther. 13(4), 419–424 (2011).
   PubMed Web of Science ®Google Scholar
• Ellingsen C, Dassau E, Zisser H Safety constraints in an artificial pancreatic beta cell: an implementation of model predictive control with insulin on board. J. Diab. Sci. Technol. 3(3), 536–544 (2009).
   PubMedGoogle Scholar
• Gillis R, Palerm CC, Zisser H, Jovanovic L, Seborg DE, Doyle FJ. Glucose estimation and prediction through meal responses using ambulatory subject data for advisory mode model predictive control. J. Diab. Sci. Technol. 1(6), 825–833 (2007).
   PubMedGoogle Scholar
• Grosman B, Dassau E, Zisser HC, Jovanovic L, Doyle FJ 3rd. Zone model predictive control: a strategy to minimize hyper- and hypoglycemic events. J. Diab. Sci. Technol. 4(4), 961–975 (2010).
   PubMedGoogle Scholar
• Hovorka R, Canonico V, Chassin LJ Nonlinear model predictive control of glucose concentration in subjects with type 1 diabetes. Physiol. Meas. 25(4), 905–920 (2004).
   PubMed Web of Science ®Google Scholar
• Kan S, Onodera H, Furutani E Novel control system for blood glucose using a model predictive method. ASAIOJ. 46(6), 657–662 (2000).
   PubMed Web of Science ®Google Scholar
• Magni L, Forgione M, Toffanin C Run-to-run tuning of model predictive control for type 1 diabetes subjects: in silico trial. J. Diab. Sci. Technol. 3(5), 1091–1098 (2009).
   PubMedGoogle Scholar
• Murphy HR, Elleri D, Allen JM Closed-loop insulin delivery during pregnancy complicated by type 1 diabetes. Diab. Care 34(2), 406–411 (2011).
   PubMed Web of Science ®Google Scholar
• Schaller HC, Schaupp L, Bodenlenz M On-line adaptive algorithm with glucose prediction capacity for subcutaneous closed loop control of glucose: evaluation under fasting conditions in patients with Type 1 diabetes. Diab. Med. 23(1), 90–93 (2006).
   PubMed Web of Science ®Google Scholar
• Schlotthauer G, Gamero LG, Torres ME, Nicolini GA. Modeling, identification and nonlinear model predictive control of type I diabetic patient. Med. Eng. Phys. 28(3), 240–250 (2006).
   PubMed Web of Science ®Google Scholar
• Wang Y, Dassau E, Doyle FJ 3rd. Closed-loop control of artificial pancreatic Beta-cell in type 1 diabetes mellitus using model predictive iterative learning control. IEEE trans. Biomed. Eng. 57(2), 211–219 (2010).
   PubMed Web of Science ®Google Scholar
• Wilinska ME, Budiman ES, Taub MB Overnight closed-loop insulin delivery with model predictive control: assessment of hypoglycemia and hyperglycemia risk using simulation studies. J. Diab. Sci. Technol. 3(5), 1109–1120 (2009).
   PubMedGoogle Scholar
• Elleri D, Dunger DB, Hovorka R. Closed-loop insulin delivery for treatment of type 1 diabetes. BMC Med. 9, 120 (2011).
   PubMed Web of Science ®Google Scholar
• Hovorka R, Kumareswaran K, Harris J Overnight closed loop insulin delivery (artificial pancreas) in adults with type 1 diabetes: crossover randomised controlled studies. BMJ 342, d1855 (2011).
   PubMedGoogle Scholar
• Nimri R, Atlas E, Ajzensztejn M, Miller S, Oron T, Phillip M. Feasibility study of automated overnight closed-loop glucose control under MD-logic artificial pancreas in patients with type 1 diabetes: the DREAM Project. Diab. Technol. Ther. 14(8), 728–735 (2012).
   PubMed Web of Science ®Google Scholar
• Hovorka R, Kremen J, Blaha J Blood glucose control by a model predictive control algorithm with variable sampling rate versus a routine glucose management protocol in cardiac surgery patients: a randomized controlled trial. J. Clin. Endocrinol. Metab. 92(8), 2960–2964 (2007).
   PubMed Web of Science ®Google Scholar
• Egi M, Finfer S, Bellomo R. Glycemic control in the ICU. Chest 140(1), 212–220 (2011).
   PubMed Web of Science ®Google Scholar
• Kavanagh BP. Glucose in the ICU - evidence, guidelines, and outcomes. N. Engl. J. Med. 367(13), 1259–1260 (2012).
   PubMed Web of Science ®Google Scholar
• Cordingley JJ, Vlasselaers D, Dormand NC Intensive insulin therapy: enhanced Model Predictive Control algorithm versus standard care. Intensive Care Med. 35(1), 123–128 (2009).
   PubMed Web of Science ®Google Scholar
• Blaha J, Kopecky P, Matias M Comparison of three protocols for tight glycemic control in cardiac surgery patients. Diab. Care 32(5), 757–761 (2009).
   PubMed Web of Science ®Google Scholar
• Breton M, Farret A, Bruttomesso D Fully integrated artificial pancreas in type 1 diabetes: modular closed-loop glucose control maintains near normoglycemia. Diabetes 61(9), 2230–2237 (2012).
   PubMed Web of Science ®Google Scholar
• Cobelli C, Renard E, Kovatchev BP Pilot studies of wearable outpatient artificial pancreas in type 1 diabetes. Diab. Care 35(9), e65–e67 (2012).
   PubMed Web of Science ®Google Scholar
• Grayson BE, Seeley RJ, Sandoval DA. Wired on sugar: the role of the CNS in the regulation of glucose homeostasis. Nat. Rev. Neurosci. 14(1), 24–37 (2013).
   PubMed Web of Science ®Google Scholar
• Teixeira RE, Malin S. The next generation of artificial pancreas control algorithms. J. Diab. Sci. Technol. 2(1), 105–112 (2008).
   PubMedGoogle Scholar
• D’Alessio DA, Vahl TP. Glucagon-like peptide 1: evolution of an incretin into a treatment for diabetes. Am. J. Physiol. Endocrinol. Metab. 286(6), E882–E890 (2004).
   Web of Science ®Google Scholar
• Bergman RN, Phillips LS, Cobelli C. Physiologic evaluation of factors controlling glucose tolerance in man: measurement of insulin sensitivity and beta-cell glucose sensitivity from the response to intravenous glucose. J. Clin. Invest. 68(6), 1456–1467 (1981).
   PubMed Web of Science ®Google Scholar
• Roy A, Parker RS. Mixed meal modeling and disturbance rejection in type I diabetic patients. Conf. Proc. 1, 323–326 (2006).
   Google Scholar
• Steil GM, Panteleon AE, Rebrin K. Closed-loop insulin delivery-the path to physiological glucose control. Adv. Drug Deliv. Rev. 56(2), 125–144 (2004).
   PubMed Web of Science ®Google Scholar
• Luzi L, DeFronzo RA. Effect of loss of first-phase insulin secretion on hepatic glucose production and tissue glucose disposal in humans. Am. J. Physiol. 257(2 Pt 1), E241–E246 (1989).
   Google Scholar
• Hartman I. Insulin analogs: impact on treatment success, satisfaction, quality of life, and adherence. Clin. Med. Res. 6(2), 54–67 (2008).
   PubMedGoogle Scholar
• Castle JR, Engle JM, El Youssef J Novel use of glucagon in a closed-loop system for prevention of hypoglycemia in type 1 diabetes. Diab. Care 33(6), 1282–1287 (2010).
   PubMed Web of Science ®Google Scholar
• El-Khatib FH, Russell SJ, Nathan DM, Sutherlin RG, Damiano ER. A bihormonal closed-loop artificial pancreas for type 1 diabetes. Sci. Trans. Med. 2(27), 27ra27 (2010).
   PubMed Web of Science ®Google Scholar
• Adeghate E, Kalasz H. Amylin analogues in the treatment of diabetes mellitus: medicinal chemistry and structural basis of its function. Open Med. Chem. J. 5(Suppl. 2), 78–81 (2011).
   PubMedGoogle Scholar
• Schmitz O, Brock B, Rungby J. Amylin agonists: a novel approach in the treatment of diabetes. Diabetes 53(Suppl. 3), S233–S238 (2004).
   PubMedGoogle Scholar
• Heptulla RA, Rodriguez LM, Mason KJ, Haymond MW. Twenty-four-hour simultaneous subcutaneous Basal-bolus administration of insulin and amylin in adolescents with type 1 diabetes decreases postprandial hyperglycemia. J. Clin. Endocrinol. Metab. 94(5), 1608–1611 (2009).
   PubMed Web of Science ®Google Scholar
• Weinzimer SA, Sherr JL, Cengiz E Effect of pramlintide on prandial glycemic excursions during closed-loop control in adolescents and young adults with type 1 diabetes. Diab. Care 35(10), 1994–1999 (2012).
   PubMed Web of Science ®Google Scholar
• Macconell L, Brown C, Gurney K, Han J. Safety and tolerability of exenatide twice daily in patients with type 2 diabetes: integrated analysis of 5594 patients from 19 placebo-controlled and comparator-controlled clinical trials. Diab. Metab. Syndr. Obes. 5, 29–41 (2012).
   PubMedGoogle Scholar
• Nikfar S, Abdollahi M, Salari P. The efficacy and tolerability of exenatide in comparison to placebo; a systematic review and meta-analysis of randomized clinical trials. J. Pharm. Pharm. Sci. 15(1), 1–30 (2012).
   PubMed Web of Science ®Google Scholar
• US Food and Drug Administration (FDA) - Center for Drug Evaluation and Research. Reports of altered kidney function in patients using exenatide (marketed as Byetta). Information for Healthcare Professionals. Marketed as Byetta, 1, (2009). www.fda.gov/Drugs/DrugSafety/PostmarketDrugSafetyInformationforPatientsandProviders/DrugSafetyInformationforHeathcareProfessionals/ucm188656.htm (Accessed 1 August 2013).
   Google Scholar
• Reichel K, Dickens L, Tellmann A, Bothe MK, Westphal M, Faisal AA. Machine Learning for Closed-loop Insulin Delivery: Model & in-vivo Studies. Conference: Bioengineering Oxford, UK, 12, (2012).
   Google Scholar
• Dazzi D, Taddei F, Gavarini A, Uggeri E, Negro R, Pezzarossa A. The control of blood glucose in the critical diabetic patient: a neuro-fuzzy method. J. Diab. Complications 15(2), 80–87 (2001).
   PubMed Web of Science ®Google Scholar
• El-Jabali AK. Neural network modeling and control of type 1 diabetes mellitus. Bioprocess Biosys. Eng. 27(2), 75–79 (2005).
   PubMed Web of Science ®Google Scholar
• Gogou G, Maglaveras N, Ambrosiadou BV, Goulis D, Pappas C. A neural network approach in diabetes management by insulin administration. J. Med. Syst. 25(2), 119–131 (2001).
   PubMedGoogle Scholar
• Mougiakakou SG, Nikita KS. A neural network approach for insulin regime and dose adjustment in type 1 diabetes. Diab. Technol. Ther. 2(3), 381–389 (2000).
   PubMedGoogle Scholar
• Otto E, Semotok C, Andrysek J, Basir O. An intelligent diabetes software prototype: predicting blood glucose levels and recommending regimen changes. Diab. Technol. Ther. 2(4), 569–576 (2000).
   PubMedGoogle Scholar
• Trajanoski Z, Regittnig W, Wach P. Simulation studies on neural predictive control of glucose using the subcutaneous route. Comput. Methods Prog. Biomed. 56(2), 133–139 (1998).
   PubMed Web of Science ®Google Scholar
• Bishop CM. Pattern Recognition and Machine Learning (Information Science and Statistics). Springer-Verlag New York, Inc., Secaucus, NJ (2006).
   Google Scholar
• Waljee AK, Higgins PD. Machine learning in medicine: a primer for physicians. Am. J. Gastroenterol. 105(6), 1224–1226 (2010).
   PubMed Web of Science ®Google Scholar
• Robertson G, Lehmann ED, Sandham W, Hamilton D. Blood glucose prediction using artificial neural networks trained with the aida diabetes simulator: a proof-of-concept pilot study. J. Electrical Comput. Eng. 2011, ID 681786 (2011).
   Google Scholar
• Zarkogianni K, Vazeou A, Mougiakakou SG, Prountzou A, Nikita KS. An insulin infusion advisory system based on autotuning nonlinear model-predictive control. IEEE Trans. Biomed. Eng. 58(9), 2467–2477 (2011).
   PubMed Web of Science ®Google Scholar
• Sutton RS, Barto AG. Reinforcement Learning: An Introduction. MIT press, Cambridge, 1(1), (1998).
   Google Scholar
• Pineau J, Guez A, Vincent R, Panuccio G, Avoli M. Treating epilepsy via adaptive neurostimulation: a reinforcement learning approach. Int. J. Neur. Sys. 19(4), 227–240 (2009).
   PubMed Web of Science ®Google Scholar
• Moore BL, Doufas AG, Pyeatt LD. Reinforcement learning: a novel method for optimal control of propofol-induced hypnosis. Anesth. Analg. 112(2), 360–367 (2011).
   PubMed Web of Science ®Google Scholar
• Sutton RS. Integrated Architectures for Learning, Planning, and Reacting Based on Approximating Dynamic Programming. In ML 216–224 (1990).
   Google Scholar
• Ernst D, Geurts P, Wehenkel L. Tree-based batch mode reinforcement learning. J. Mach. Learn. Res. 6, 503–556 (2005).
   Web of Science ®Google Scholar
• Ernst D, Stan G-B, Goncalves J, Wehenkel L. Clinical Data Based Optimal STI Strategies for HIV; A Reinforcement Learning Approach. In Decision and Control, 2006 45th IEEE Conference on 667–672, IEEE (2006).
   Google Scholar
• Deisenroth MP, Rasmussen CE. PILCO: A Model-Based and Data-Efficient Approach to Policy Search. In Proceedings of the 28th International Conference on Machine Learning, Bellevue, Washington, USA (ICML-11) 465–472 (2011).
   Google Scholar
• Gaweda AE, Muezzinoglu MK, Jacobs AA, Aronoff GR, Brier ME. Model predictive control with reinforcement learning for drug delivery in renal anemia management. Conf. Proc. 1, 5177–5180 (2006).
   Google Scholar
• Moore BL, Quasny TM, Doufas AG. Reinforcement learning versus proportional-integral-derivative control of hypnosis in a simulated intraoperative patient. Anesth. Analg. 112(2), 350–359 (2011).
   PubMed Web of Science ®Google Scholar
• Daskalaki E, Diem P, Mougiakakou SG. An Actor-Critic based controller for glucose regulation in type 1 diabetes. Comput. Methods Prog. Biomed. 109(2), 116–125. (2013).
   PubMed Web of Science ®Google Scholar