Unsupervised calibration for noninvasive glucose-monitoring devices using mid-infrared spectroscopy
Unsupervised calibration for noninvasive glucose-monitoring devices using mid-infrared spectroscopy
复制标题
DOI：
10.1142/s1793545818500384
复制
发表时间：
2018-11-01
影响因子：
2.5
通讯作者：
Matsuura, Yuji
中科院分区：
文献类型：
--
作者：
Kasahara, Ryosuke;Kino, Saiko;Matsuura, Yuji
已研究的使用红外光谱的无创血糖监测技术通常需要涉及血液采集的校准过程，这使得这些方法具有一定的侵入性。我们开发了一种真正的无创血糖监测技术，使用中红外光谱，不需要采集血液进行校准，通过使用深度神经网络应用域适应（DA）来训练将血糖浓度与中红外光谱数据相关联的模型，而不需要标有侵入性血液样本测量值的训练数据集。为了实现DA，在训练网络期间通过对抗性更新来考虑用于校准的未标记光谱数据的分布，以回归血糖浓度。该校准将真实血糖浓度与预测血糖浓度之间的相关系数从 0.38 提高到 0.47。结果表明，这种校准技术提高了中红外葡萄糖测量的预测准确性，而无需任何侵入式采集数据。
Noninvasive, glucose-monitoring technologies using infrared spectroscopy that have been studied typically require a calibration process that involves blood collection, which renders the methods somewhat invasive. We develop a truly noninvasive, glucose-monitoring technique using mid-infrared spectroscopy that does not require blood collection for calibration by applying domain adaptation (DA) using deep neural networks to train a model that associates blood glucose concentration with mid-infrared spectral data without requiring a training dataset labeled with invasive blood sample measurements. For realizing DA, the distribution of unlabeled spectral data for calibration is considered through adversarial update during training networks for regression to blood glucose concentration. This calibration improved the correlation coefficient between the true blood glucose concentrations and predicted blood glucose concentrations from 0.38 to 0.47. The result indicates that this calibration technique improves prediction accuracy for mid-infrared glucose measurements without any invasively acquired data.