A multi-objective optimal insulin bolus advisor for type 1 diabetes based on personalized model and daily diet

We proposed a personalized bolus advisor for patients with type 1 diabetes (T1D). A bolus advisor is a decision support system that recommends insulin doses based on an open-loop model-based optimization. To construct the bolus advisor, the optimal open-loop control of blood glucose (BG) concentration in T1D patients was represented as a multi-objective optimization problem. The insulin types, doses, and times for each injection were provided by the bolus advisor based on a personalized model and an average daily diet, which should be re-tuned frequently in specific time intervals. The constructed personalized model for T1D patients incorporates effects of the patient's age and body weight. Two treatment schemes using three types of insulin (regular, lispro, and NPH) were investigated. The proposed bolus advisor was tested in silico on three virtual patients with different ages (from 9 to 50 years old) and body weights (from 28 to 100 kg) considering +/- 40% under- and over-eating scenarios. The fluctuations in blood glucose and insulin levels are obviously wider in younger virtual subjects, which is showing the difficulties of the BG control problem in younger patients.