Neural network-based model predictive control for type 1 diabetic rats on artificial pancreas system
- 157 Downloads
Artificial pancreas system (APS) is a viable option to treat diabetic patients. Researchers, however, have not conclusively determined the best control method for APS. Due to intra-/inter-variability of insulin absorption and action, an individualized algorithm is required to control blood glucose level (BGL) for each patient. To this end, we developed model predictive control (MPC) based on artificial neural networks (ANNs), which combines ANN for BGL prediction based on inputs and MPC for BGL control based on the ANN (NN-MPC). First, we developed a mathematical model for diabetic rats, which was used to identify individual virtual subjects by fitting to empirical data collected through an APS, including BGL data, insulin injection, and food intake. Then, the virtual subjects were used to generate datasets for training ANNs. The NN-MPC determines control actions (insulin injection) based on BGL predicted by the ANN. To evaluate the NN-MPC, we conducted experiments using four virtual subjects under three different scenarios. Overall, the NN-MPC maintained BGL within the normal range about 90% of the time with a mean absolute deviation of 4.7 mg/dl from a desired BGL. Our findings suggest that the NN-MPC can provide subject-specific BGL control in conjunction with a closed-loop APS.
KeywordsArtificial neural network Artificial pancreas system Blood glucose level control Model predictive control Type 1 diabetes mellitus
Compliance with ethical standards
All animal maintenance and treatment protocols complied with the Guide for Care and Use of Laboratory Animals as adopted by the National Institute of Health and approved by the Southern Illinois University Edwardsville (SIUE) Institutional Animal Care and Use Committee (IACUC).
- 8.Bergman RN, Ider YZ, Bowden CR, Cobelli C (1979) Quantitative estimation of insulin sensitivity. Am J Phys 236:E667–E677Google Scholar
- 18.Patek SD, Bequette BW, Breton M, Buckingham BA, Dassau E, Doyle FJ 3rd, Lum J, Magni L, Zisser H (2009) In silico preclinical trials: methodology and engineering guide to closed-loop control in type 1 diabetes mellitus. J Diabetes Sci Technol 3:269–282. https://doi.org/10.1177/193229680900300207 CrossRefPubMedPubMedCentralGoogle Scholar
- 20.Zarkogianni K, Mougiakakou SG, Prountzou A, Vazeou A, Bartsocas CS, Nikita KS (2007) An insulin infusion advisory system for type 1 diabetes patients based on non-linear model predictive control methods. Conf Proc IEEE Eng Med Biol Soc 2007:5972–5975. https://doi.org/10.1109/IEMBS.2007.4353708 CrossRefPubMedGoogle Scholar
- 24.Perez-Gandia C, Facchinetti A, Sparacino G, Cobelli C, Gomez EJ, Rigla M, de Leiva A, Hernando ME (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 CrossRefPubMedGoogle Scholar
- 30.Brenner M, Abadi SEM, Balouchzadeh R, Lee HF, Ko HS, Johns M, Malik N, Lee JJ, Kwon G (2017) Estimation of insulin secretion, glucose uptake by tissues, and liver handling of glucose using a mathematical model of glucose-insulin homeostasis in lean and obese mice. Heliyon 3:e00310. https://doi.org/10.1016/j.heliyon.2017.e00310 CrossRefPubMedPubMedCentralGoogle Scholar
- 32.Park S, Balouchzadeh R, Ko HS, Lee HF, Kwon G Establishing an animal model artificial pancreas system to study blood glucose levels in real-time. In: Proceedings of the 2017 BMES Annual Meeting, Abstract nr FRI-513Google Scholar