Patient-specific deep offline artificial pancreas for blood glucose regulation in type 1 diabetes

Due to insufficient insulin secretion, patients with type 1 diabetes mellitus (T1DM) are prone to blood glucose fluctuations ranging from hypoglycemia to hyperglycemia. While dangerous hypoglycemia may lead to coma immediately, chronic hyperglycemia increases patients risks for cardiorenal and vascular diseases in the long run. In principle, an artificial pancreas - a closed-loop insulin delivery system requiring patients manually input insulin dosage according to the upcoming meals - could supply exogenous insulin to control the glucose levels and hence reduce the risks from hyperglycemia. However, insulin overdosing in some type 1 diabetic patients, who are physically active, can lead to unexpected hypoglycemia beyond the control of common artificial pancreas. Therefore, it is important to take into account the glucose decrease due to physical exercise when designing the next-generation artificial pancreas. In this work, we develop a deep reinforcement learning algorithm using a T1DM dataset, containing data from wearable devices, to automate insulin dosing for patients with T1DM. In particular, we build patient-specific computational models using systems biology informed neural networks (SBINN), to mimic the glucose-insulin dynamics for a few patients from the dataset, by simultaneously considering patient-specific carbohydrate intake and physical exercise intensity.