School of Electrical Engineering and Computer Science, Ohio University, Athens, OH 45701, USA.
Department of Computer Science, University of North Carolina at Charlotte, Charlotte, NC 28223, USA.
Sensors (Basel). 2021 May 10;21(9):3303. doi: 10.3390/s21093303.
To avoid serious diabetic complications, people with type 1 diabetes must keep their blood glucose levels (BGLs) as close to normal as possible. Insulin dosages and carbohydrate consumption are important considerations in managing BGLs. Since the 1960s, models have been developed to forecast blood glucose levels based on the history of BGLs, insulin dosages, carbohydrate intake, and other physiological and lifestyle factors. Such predictions can be used to alert people of impending unsafe BGLs or to control insulin flow in an artificial pancreas. In past work, we have introduced an LSTM-based approach to blood glucose level prediction aimed at "what-if" scenarios, in which people could enter foods they might eat or insulin amounts they might take and then see the effect on future BGLs. In this work, we invert the "what-if" scenario and introduce a similar architecture based on chaining two LSTMs that can be trained to make either insulin or carbohydrate recommendations aimed at reaching a desired BG level in the future. Leveraging a recent state-of-the-art model for time series forecasting, we then derive a novel architecture for the same recommendation task, in which the two LSTM chain is used as a repeating block inside a deep residual architecture. Experimental evaluations using real patient data from the OhioT1DM dataset show that the new integrated architecture compares favorably with the previous LSTM-based approach, substantially outperforming the baselines. The promising results suggest that this novel approach could potentially be of practical use to people with type 1 diabetes for self-management of BGLs.
为避免严重的糖尿病并发症，1 型糖尿病患者必须尽可能将血糖水平（BGL）保持在接近正常的水平。胰岛素剂量和碳水化合物的消耗是管理 BGL 的重要考虑因素。自 20 世纪 60 年代以来，已经开发出了基于 BGL 历史、胰岛素剂量、碳水化合物摄入量以及其他生理和生活方式因素来预测血糖水平的模型。这些预测可以用于提醒人们即将出现不安全的 BGL，或者控制人工胰腺中的胰岛素流量。在过去的工作中，我们引入了一种基于 LSTM 的血糖水平预测方法，旨在针对“假设”情况，人们可以输入他们可能吃的食物或可能服用的胰岛素量，然后查看对未来 BGL 的影响。在这项工作中，我们反转了“假设”情况，并引入了一种类似的架构，该架构基于链式两个 LSTM，这两个 LSTM 可以接受训练，目的是在未来达到理想的血糖水平，从而提供胰岛素或碳水化合物建议。利用最近用于时间序列预测的最先进模型，我们为相同的推荐任务推导出了一种新颖的架构，其中两个 LSTM 链作为深度残差架构中的重复块。使用来自俄亥俄州 1 型糖尿病数据集的真实患者数据进行的实验评估表明，新的集成架构与以前基于 LSTM 的方法相比具有优势，大大优于基线。有希望的结果表明，这种新方法对于 1 型糖尿病患者自我管理 BGL 可能具有实际用途。
