Offline Reinforcement Learning for Safer Blood Glucose Control in People with Type 1 Diabetes
This work addresses the challenge of safer and more effective glucose management for individuals with type 1 diabetes, representing an incremental improvement over existing online reinforcement learning methods by eliminating the need for risky patient interaction during training.
This paper tackles the problem of improving blood glucose control in people with type 1 diabetes by using offline reinforcement learning to develop safer insulin dosing policies, achieving a significant increase in time spent in the healthy blood glucose range from 61.6% to 65.3% compared to the strongest baseline without increasing low blood glucose events.
The widespread adoption of effective hybrid closed loop systems would represent an important milestone of care for people living with type 1 diabetes (T1D). These devices typically utilise simple control algorithms to select the optimal insulin dose for maintaining blood glucose levels within a healthy range. Online reinforcement learning (RL) has been utilised as a method for further enhancing glucose control in these devices. Previous approaches have been shown to reduce patient risk and improve time spent in the target range when compared to classical control algorithms, but are prone to instability in the learning process, often resulting in the selection of unsafe actions. This work presents an evaluation of offline RL for developing effective dosing policies without the need for potentially dangerous patient interaction during training. This paper examines the utility of BCQ, CQL and TD3-BC in managing the blood glucose of the 30 virtual patients available within the FDA-approved UVA/Padova glucose dynamics simulator. When trained on less than a tenth of the total training samples required by online RL to achieve stable performance, this work shows that offline RL can significantly increase time in the healthy blood glucose range from 61.6 +\- 0.3% to 65.3 +/- 0.5% when compared to the strongest state-of-art baseline (p < 0.001). This is achieved without any associated increase in low blood glucose events. Offline RL is also shown to be able to correct for common and challenging control scenarios such as incorrect bolus dosing, irregular meal timings and compression errors.