%L discovery10117791
%I Springer
%E A Shaban-Nejad
%E M Michalowski
%E DL Buckeridge
%O This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
%A T Zhu
%A K Li
%A P Georgiou
%J Studies in Computational Intelligence
%X We introduce a dual-hormone control algorithm for people with Type 1 Diabetes (T1D) which uses deep reinforcement learning (RL). Specifically, double dilated recurrent neural networks are used to learn the control strategy, trained by a variant of Q-learning. The inputs to the model include the real-time sensed glucose and meal carbohydrate content, and the outputs are the actions necessary to deliver dual-hormone (basal insulin and glucagon) control. Without prior knowledge of the glucose-insulin metabolism, we develop a data-driven model using the UVA/Padova Simulator. We first pre-train a generalized model using long-term exploration in an environment with average T1D subject parameters provided by the simulator, then adopt importance sampling to train personalized models for each individual. In-silico, the proposed algorithm largely reduces adverse glycemic events, and achieves time in range, i.e., the percentage of normoglycemia,   93%  for the adults and   83%  for the adolescents, which outperforms previous approaches significantly. These results indicate that deep RL has great potential to improve the treatment of chronic diseases such as diabetes.
%P 45-53
%B Explainable AI in Healthcare and Medicine
%T Personalized Dual-Hormone Control for Type 1 Diabetes Using Deep Reinforcement Learning
%D 2020
%C Cham, Switzerland
%S Studies in Computational Intelligence
%V 914