@inproceedings{discovery10117791,
           title = {Personalized Dual-Hormone Control for Type 1 Diabetes Using Deep Reinforcement Learning},
          series = {Studies in Computational Intelligence},
            year = {2020},
          volume = {914},
          editor = {A Shaban-Nejad and M Michalowski and DL Buckeridge},
         journal = {Studies in Computational Intelligence},
           pages = {45--53},
         address = {Cham, Switzerland},
       booktitle = {Explainable AI in Healthcare and Medicine},
       publisher = {Springer},
            note = {This version is the author accepted manuscript. For information on re-use, please refer to the publisher's terms and conditions.},
        abstract = {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.},
          author = {Zhu, T and Li, K and Georgiou, P},
             url = {https://doi.org/10.1007/978-3-030-53352-6\%5f5}
}