Neural network-based model predictive control for type 1 diabetic rats on artificial pancreas system

Abstract

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. Graphical abstract ᅟ.

An adaptive control scheme for Interleukin-2 therapy

“…Mathematical description of IL-2 therapy After intravenous administration of a drug, instantaneous jumps are observed in the drug concentration in plasma and target organ (22). In the framework of mathematical modeling, systems with discontinuities in their dynamics can be categorized as impulsive systems and allows for application of control engineering design tools (19,20,(23)(24)(25)(26)(27)(28)(29)(30)(31). Among these methods, model predictive control (MPC) techniques have been widely used (19,20,(23)(24)(25)(26)(27)(28) due to their ability to consider systemic constraints, which confine the dynamics of the system variables or the external control input.…”

An adaptive technique based blood glucose control in type‐1 diabetes mellitus patients

“…Bahremand et al 28 have predicted blood glucose level (BGL) followed with the combination of artificial neural networks (ANNs) to a model predictive control (MPC). At first, the individual virtual subjects for diabetic rats were obtained through developing a mathematical model that suits better the data obtained based on food intake, insulin injection, and BGL data.…”

An Adaptive Control Scheme for Interleukin-2 Therapy

“…After intravenous administration of a drug, instantaneous jumps are observed in the drug concentration in plasma and the target organ (Yang, 2001 iScience Article discontinuities in their dynamics can be categorized as impulsive systems and allow for application of control engineering design tools (Sopasakis et al, 2015;Rivadeneira et al, 2015Rivadeneira et al, , 2016Rivadeneira et al, , 2017Gonzá lez et al, 2017;Fontes and Pereira, 2012;Magni et al, 2007;Bahremand et al, 2019;Montaseri et al, 2018Montaseri et al, , 2020Rivadeneira and Moog, 2012). Among these methods, model predictive control (MPC) techniques have been widely used (Sopasakis et al, 2015;Rivadeneira et al, 2015Rivadeneira et al, , 2016Rivadeneira et al, , 2017Gonzá lez et al, 2017;Fontes and Pereira, 2012;Magni et al, 2007;Bahremand et al, 2019) due to their ability to consider systemic constraints, which confine the dynamics of the system variables or the external control input. In the context of pharmacodynamics, the control input is the administered drug.…”