Challenging common bolus advisor for self-monitoring type-I diabetes patients using Reinforcement Learning

A lot of the research around blood glucose management for diabetes focuses on the artificial pancreas, so the case Patients with diabetes who are self-monitoring have to decide right where the patient is equipped with an insulin pump. The interested before each meal how much insulin they should take. A standard bolus reader can find an extensive review here [1]. For self-monitoring, advisor exists, but has never actually been proven to be optimal [6] worked on the best delivery of insulin drugs to facilitate BG in any sense. We challenged this rule applying Reinforcement Learning management. Based on a complex diabetes simulator, the authors techniques on data simulated with T1DM, an FDAapproved of [2] and [7] worked on learning adaptively coefficients (CIR, CF) simulator developped by [3] modeling the gluco-insulin interaction.