Subcutaneous neural inverse optimal control for an Artificial Pancreas

Type 1 Diabetes mellitus (T1DM) is a chronic disease that occurs when the body cannot produce insulin. Since insulin was discovered in 1920, the way to keep T1DM patients blood glucose at normal levels has been insulin injections, via subcutaneous or intravenous paths. The efforts for an external infusion therapy have resulted in the so-called Artificial Pancreas. Such device attempts to integrate continuous insulin infusion, continuous glucose monitoring and an automatic control algorithm, which calculates the required insulin infusion. Considering all the problems related to T1DM, in this paper a neural model which captures the nonlinear behavior of the complex glucose-insulin dynamics is proposed; based on this model, a control algorithm is developed using the neural inverse optimal control via control lyapunov function (CLF) technique. Simulation results illustrate the applicability of the propounded scheme.