Challenging common bolus advisor for self-monitoring type-I diabetes patients using Reinforcement Learning
This addresses a critical safety issue for self-monitoring diabetes patients by potentially improving insulin dosing decisions, though it is incremental as it builds on existing simulation methods.
The study tackled the problem of determining optimal insulin bolus doses for type-I diabetes patients by challenging the standard bolus advisor using Reinforcement Learning on simulated data, showing that the optimal rule differs significantly and can avoid hypoglycemia episodes.
Patients with diabetes who are self-monitoring have to decide right before each meal how much insulin they should take. A standard bolus advisor exists, but has never actually been proven to be optimal in any sense. We challenged this rule applying Reinforcement Learning techniques on data simulated with T1DM, an FDA-approved simulator developed by Kovatchev et al. modeling the gluco-insulin interaction. Results show that the optimal bolus rule is fairly different from the standard bolus advisor, and if followed can actually avoid hypoglycemia episodes.