People with Type 1 diabetes (T1D) require regular exogenous infusion of insulin to maintain their blood glucose concentration in a therapeutically adequate target range. Although the artificial pancreas and continuous glucose monitoring have been proven to be effective in achieving closed-loop control, significant challenges still remain due to the high complexity of glucose dynamics and limitations in the technology. In this work, we propose a novel deep reinforcement learning model for single-hormone (insulin) and dual-hormone (insulin and glucagon) delivery. In particular, the delivery strategies are developed by double Q-learning with dilated recurrent neural networks. For designing and testing purposes, the FDA-accepted UVA/Padova Type 1 simulator was employed. First, we performed long-term generalized training to obtain a population model. Then, this model was personalized with a small data-set of subject-specific data. In silico results show that the single and dual-hormone delivery strategies achieve good glucose control when compared to a standard basal-bolus therapy with low-glucose insulin suspension. Specifically, in the adult cohort (n = 10), percentage time in target range 70, 180 mg/dL improved from 77.6% to 80.9% with single-hormone control, and to 85.6% with dual-hormone control. In the adolescent cohort (n = 10), percentage time in target range improved from 55.5% to $\text{65.9}\%$ with single-hormone control, and to 78.8% with dual-hormone control. In all scenarios, a significant decrease in hypoglycemia was observed. These results show that the use of deep reinforcement learning is a viable approach for closed-loop glucose control in T1D.

中文翻译：

---

使用深度强化学习控制 1 型糖尿病的基础葡萄糖：计算机验证

1 型糖尿病 (T1D) 患者需要定期外源性胰岛素输注，以将血糖浓度维持在足够治疗的目标范围内。尽管人工胰腺和连续血糖监测已被证明在实现闭环控制方面是有效的，但由于葡萄糖动力学的高度复杂性和技术的局限性，仍然存在重大挑战。在这项工作中，我们提出了一种用于单激素（胰岛素）和双激素（胰岛素和胰高血糖素）递送的新型深度强化学习模型。特别是，交付策略是通过双 Q 学习和扩张的循环神经网络开发的。出于设计和测试目的，采用了 FDA 认可的 UVA/Padova 1 型模拟器。首先，我们进行了长期的泛化训练以获得人口模型。电脑模拟结果表明，与使用低葡萄糖胰岛素悬浮液的标准基础推注疗法相比，单激素和双激素递送策略实现了良好的血糖控制。具体而言，在成人队列 (n = 10) 中，目标范围 70, 180 mg/dL 的百分比时间从 77.6% 提高到 80.9%，单激素控制，双激素控制的 85.6%。在青少年队列 (n = 10) 中，目标范围内的时间百分比从 55.5% 提高到$\text{65.9}\%$单激素控制，双激素控制达到 78.8%。在所有情况下，均观察到低血糖显着减少。这些结果表明，在 T1D 中使用深度强化学习是一种可行的闭环血糖控制方法。