Abstract: Presented herein are methods, and devices of adaptively tuning a zone based Model Predictive Control (MPC) controller, using at least one processor, which include determining, residuals based on prediction models storing, in a memory, the determined residuals, calculating a trust index by quantifying uncertainty of the prediction models using the stored residuals and tuning the MPC controller, in real time based on the calculated value of the trust index.

Abstract: The present disclosure provides a hypoglycemia prediction algorithm (HPA) specifically designed for the unique postprandial glycemic patterns characteristic of PBH. This algorithm can predict impending hypoglycemia by performing a series of steps. The steps can include collecting data from at least one sensor. The data can comprise a concentration of glucose in the bloodstream of a subject. The data can be processed using the HPA and impending glucose concentrations can be calculated. The method can then provide for determining whether the predicted glucose concentrations are lower than a hypoglycemic threshold parameter. In response to determining that the predicted glucose concentrations are lower than the hypoglycemic threshold parameter, the method can provide for enacting an impending hypoglycemia protocol.