Investigating Potentials and Pitfalls of Knowledge Distillation Across Datasets for Blood Glucose Forecasting
Investigating Potentials and Pitfalls of Knowledge Distillation Across Datasets for Blood Glucose Forecasting
复制标题
DOI：
--
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Hadia Hameed;Samantha Kleinberg
中科院分区：
文献类型：
--
作者：
Hadia Hameed;Samantha Kleinberg
。 I 型糖尿病 (T1D) 患者必须经常监测血糖 (BG) 并注射胰岛素来调节血糖。连续血糖监测仪 (CGM) 和胰岛素泵等新设备通过促进自动输送胰岛素的人工胰腺 (AP) 等闭环技术，帮助减轻了这一负担。随着越来越多的人使用依赖 CGM 和胰岛素泵的 AP 系统，T1D 患者生成的大规模健康数据 (PGHD) 的可用性急剧增加。这些数据可用于训练强大的、可泛化的模型，以进行准确的 BG 预测，然后可用于对 OhioT1DM 等较小的数据集进行实时预测。在这项工作中，我们研究了使用知识蒸馏将知识从一个数据集学习的模型转移到另一个数据集的潜力和陷阱，并将其与单独使用任一数据集的基线情况进行比较。我们表明，使用预训练模型仅根据 CGM 数据（单变量设置）对 OhioT1DM 进行 BG 预测，其性能与 OhioT1DM 本身的训练相当。使用仅在 OhioT1DM 数据上训练的单步单变量循环神经网络 (RNN)，我们在 30 分钟和 60 分钟的预测范围 (PH) 下分别实现了 19.21 和 31.77 mg/dl 的总体 RMSE。
. Individuals with Type I diabetes (T1D) must frequently monitor their blood glucose (BG) and deliver insulin to regulate it. New devices like continuous glucose monitors (CGMs) and insulin pumps have helped reduce this burden by facilitating closed-loop technologies like the artifical pancreas (AP) for delivering insulin automatically. As more people use AP systems, which rely on a CGM and insulin pump, there has been a dramatic increase in the availability of large scale patient-generated health data (PGHD) in T1D. This data can potentially be used to train robust, generalizable models for accurate BG forecasting which can then be used to make forecasts for smaller datasets like OhioT1DM in real-time. In this work, we investigate the potential and pitfalls of using knowledge distillation to transfer knowledge from a model learned from one dataset to another and compare it with the baseline case of using either dataset alone. We show that using a pre-trained model to do BG forecasting for OhioT1DM from CGM data only (univariate setting) has comparable performance to training on OhioT1DM itself. Using a single-step, univariate recurrent neural network (RNN) trained on OhioT1DM data alone, we achieve an overall RMSE of 19.21 and 31.77 mg/dl for a prediction horizon (PH) of 30 and 60 minutes respectively.