Context-aware system for glycemic control in diabetic patients using neural networks
Context-aware system for glycemic control in diabetic patients using neural networks
Diabetic patients are quite hesitant in engaging in normal physiological activities due to difficulties associatedwith diabetes management. Over the last few decades, there have been advancements in the computational power ofembedded systems and glucose sensing technologies. These advancements have attracted the attention of researchersaround the globe developing automatic insulin delivery systems. In this paper, a method of closed-loop control of diabetesbased on neural networks is proposed. These neural networks are used for making predictions based on the clinical data ofa patient. A neural network feedback controller is also designed to provide a glycemic response by regulating the insulininfusion rate. An activity recognition model based on convolutional neural networks is also proposed for predicting thepatient’s current physical activity. Predictions from this model are transformed into a six-level code and are fed as inputto the neural network glucose prediction model. Experimental results of the proposed system show good performance inkeeping blood glucose levels in the nondiabetic range.
___
- [1] Centers for Disease Control and Prevention. National Diabetes Fact Sheet. Atlanta, GA, USA: Centers for Disease
Control and Prevention, 2005.
- [2] Gerich JE. The importance of tight glycemic control. American Journal of Medicine. 2005; 118 (9): 7-11. doi:
10.1016/j.amjmed.2005.07.051
- [3] World Health Organization. Diagnosis of Diabetes Mellitus and Intermediate Hyperglycemia: Report of a WHO/IDF
Consultation. Geneva, Switzerland: World Health Organization, 2006.
- [4] Khattab M, Khader YS, Al-Khawaldeh A, Ajlouni K. Factors associated with poor glycemic control among
patients with Type 2 diabetes. Journal of Diabetes and Its Complications 2010; 24 (2): 84–89. doi:
10.1016/j.jdiacomp.2008.12.008
- [5] Al-Khawaldeh OA, Al-Hassan MA, Froelicher ES. Self-efficacy, self-management, and glycemic control in
adults with type 2 diabetes mellitus. Journal of Diabetes and Its Complications 2012; 26 (1): 10–16. doi:
10.1016/j.jdiacomp.2011.11.002
- [6] Weissberg-Benchell J, Antisdel-Lomaglio J, Seshadri R. Insulin pump therapy: a meta-analysis. Diabetes Care 2003;
26 (4): 1079–1087. doi: 10.2337/diacare.26.4.1079
- [7] Dolgin E. Managed by machine. Nature 2012; 485 (7398): S6-S8. doi: 10.1038/485S6a
- [8] Karatoprak C, Yolbas S, Kiskac M, Zorlu M, Yay A et al. The effects of short-acting analogue insulins on body
weight in patients with type 2 diabetes mellitus. Turkish Journal of Medical Sciences 2013; 43 (2): 268-272. doi:
10.3906/sag-1201-77
- [9] Clarke WL, Anderson S, Breton M, Patek S, Kashmer L et al. Closed-loop artificial pancreas using subcutaneous
glucose sensing and insulin delivery and a model predictive control algorithm: the Virginia experience. Journal of
Diabetes Science and Technology 2009; 3 (5): 1031–1038. doi: 10.1177/193229680900300506
- [10] Chassin LJ, Wilinska ME, Hovorka R. Evaluation of glucose controllers in virtual environment: methodology and
sample application. Artificial Intelligence in Medicine 2004; 32 (3): 171-181. doi: 10.1016/j.artmed.2004.02.006
- [11] Soylu S, Danisman K. Blood glucose control using an ABC algorithm-based fuzzy-PID controller. Turkish Journal
of Electrical Engineering & Computer Sciences 2018; 26: 172–183. doi: 10.3906/elk-1704-203
- [12] Dassau E, Palerm CC, Zisser H, Buckingham BA, Jovanovič L et al. In silico evaluation platform for artificial
pancreatic β -cell development—a dynamic simulator for closed-loop control with hardware-in-the-loop. Diabetes
Technology & Therapeutics 2009; 11 (3): 187–194. doi: 10.1089/dia.2008.0055
- [13] Bequette BW. A critical assessment of algorithms and challenges in the development of a closed-loop artificial
pancreas. Diabetes Technology & Therapeutics 2005; 7 (1): 28–47. doi: 10.1089/dia.2005.7.28
- [14] El-Khatib FH, Russell SJ, Nathan DM, Sutherlin RG, Damiano ER. A bihormonal closed-loop artificial pancreas
for type 1 diabetes. Science Translational Medicine 2010; 2 (27): 27ra27–27ra27. doi: 10.1126/scitranslmed.3000619
- [15] Kovatchev B, Patek S, Dassau E, Doyle FJ, Magni L et al. Control to range for diabetes: functionality and modular
architecture. Journal of Diabetes Science and Technology 2009; 3 (5): 1058–1065. doi: 10.1177/193229680900300509
- [16] Turksoy K, Samadi S, Feng J, Littlejohn E, Quinn L et al. Meal detection in patients with type 1 diabetes: a new
module for the multivariable adaptive artificial pancreas control system. IEEE Journal of Biomedical and Health
Informatics 2016; 20 (1): 47–54. doi: 10.1109/jbhi.2015.2446413
- [17] Colberg SR, Laan R, Dassau E, Kerr D. Physical activity and type 1 diabetes: time for a rewire? Journal of
Diabetes Science and Technology 2015; 9 (3): 609-618. doi: 10.1177/1932296814566231
- [18] Breton MD, Brown SA, Karvetski CH, Kollar L, Topchyan KA et al. Adding heart rate signal to a control-to-range
artificial pancreas system improves the protection against hypoglycemia during exercise in type 1 diabetes. Diabetes
Technology & Therapeutics 2014; 16(8): 506-511. doi: 10.1089/dia.2013.0333
- [19] Stenerson M, Cameron F, Payne SR, Payne SL, Ly TT et al. The impact of accelerometer use in exercise-associated
hypoglycemia prevention in type 1 diabetes. Journal of Diabetes Science and Technology 2014; 9 (1): 80-85. doi:
10.1177/1932296814551045
- [20] Turksoy K, Quinn LT, Littlejohn E, Cinar A. An integrated multivariable artificial pancreas control system. Journal
of Diabetes Science and Technology 2014; 8 (3): 498-507. doi: 10.1177/1932296814524862
- [21] Pappada SM, Cameron BD, Rosman PM, Bourey RE, Papadimos TJ et al. Neural network-based real-time prediction of glucose in patients with insulin-dependent diabetes. Diabetes Technology & Therapeutics 2011; 13 (2):
135–141. doi: 10.1089/dia.2010.0104
- [22] Facchinetti A, Sparacino G, Trifoglio E, Cobelli C. A new index to optimally design and compare continuous
glucose monitoring glucose prediction algorithms. Diabetes Technology & Therapeutics 2011; 13 (2): 111–119. doi:
10.1089/dia.2010.0151
- [23] 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. Journal of Electrical and Computer
Engineering 2011; 2011: 1–11. doi: 10.1155/2011/681786
- [24] De Leiva-Hidalgo A, de Leiva-Pérez A, Bruguès-Bruguès E. From pancreatic extracts to artificial pancreas: history,
science and controversies about the discovery of the pancreatic antidiabetic hormone. Avances en Diabetología 2011;
27 (1): 15–26. doi: 10.1016/s1134-3230(11)70004-7
- [25] Mussi S. Cheerup: A general software-environment for building, using and administering predictive monitoring
portals. Advances in Electrical and Computer Engineering 2011; 11 (4): 63–70. doi: 10.4316/aece.2011.04010
- [26] Mougiakakou SG, Prountzou K, Nikita KS. A real time simulation model of glucose-insulin metabolism for type 1
diabetes patients. In: IEEE 2005 Engineering in Medicine and Biology 27th Annual Conference; Shanghai, China;
2005. pp. 298-301.
- [27] Grosman B, Dassau E, Zisser HC, Jovanovič L, Doyle FJ. Zone model predictive control: a strategy to minimize hyper- and hypoglycemic events. Journal of Diabetes Science and Technology 2010; 4 (4): 961–975. doi:
10.1177/193229681000400428
- [28] Riddell M, Perkins BA. Exercise and glucose metabolism in persons with diabetes mellitus: perspectives on the
role for continuous glucose monitoring. Journal of Diabetes Science and Technology 2009; 3 (4): 914–923. doi:
10.1177/193229680900300439
- [29] Steil GM, Rebrin K, Hariri F, Jinagonda S, Tadros S et al. Interstitial fluid glucose dynamics during insulin-induced
hypoglycaemia. Diabetologia 2005; 48 (9): 1833–1840. doi: 10.1007/s00125-005-1852-x
- [30] Percival MW, Bevier WC, Wang Y, Dassau E, Zisser HC et al. Modeling the effects of subcutaneous insulin
administration and carbohydrate consumption on blood glucose. Journal of Diabetes Science and Technology 2010;
4 (5): 1214–1228. doi: 10.1177/193229681000400522
- [31] Hagan MT, Demuth HB, Jesús OD. An introduction to the use of neural networks in control systems. International
Journal of Robust and Nonlinear Control 2002; 12 (11): 959–985. doi: 10.1002/rnc.727
- [32] Mukherjee I, Routroy S. Comparing the performance of neural networks developed by using Levenberg–Marquardt
and Quasi-Newton with the gradient descent algorithm for modelling a multiple response grinding process. Expert
Systems with Applications 2012; 39 (3): 2397-2407. doi: 10.1016/j.eswa.2011.08.087
- [33] Ata S, Khan ZH. Model based control of artificial pancreas under meal disturbances. In: 2017 International
Symposium on Recent Advances in Electrical Engineering; 2017. pp. 1-6. doi: 10.1109/RAEE.2017.8246033