Phang Chun-Ren, Hirata Akimasa
Department of Electrical and Mechanical Engineering, and the Center of Biomedical Physics and Information Technology, Nagoya Institute of Technology, Gokiso-cho, Showa-ku, Nagoya 466-8555 Aichi, Japan.
DNAKE BCI Lab, Brain-Computer Interaction Business Unit, DNAKE (Xiamen) Intelligent Technology CO., LTD, Xiamen, Fujian, People's Republic of China.
J Neural Eng. 2025 Mar 7;22(2). doi: 10.1088/1741-2552/adb90c.
Humans spend a significant portion of their lives in sleep (an essential driver of body metabolism). Moreover, as sleep deprivation could cause various health complications, it is crucial to develop an automatic sleep stage detection model to facilitate the tedious manual labeling process. Notably, recently proposed sleep staging algorithms lack model explainability and still require performance improvement.We implemented multiscale neurophysiology-mimicking kernels to capture sleep-related electroencephalogram (EEG) activities at varying frequencies and temporal lengths; the implemented model was named 'multiscale temporal convolutional neural network (MTCNN).' Further, we evaluated its performance using an open-source dataset (Sleep-EDF Database Expanded comprising 153 d of polysomnogram data).By investigating the learned kernel weights, we observed that MTCNN detected the EEG activities specific to each sleep stage, such as the frequencies, K-complexes, and sawtooth waves. Furthermore, regarding the characterization of these neurophysiologically significant features, MTCNN demonstrated an overall accuracy (OAcc) of 91.12% and a Cohen kappa coefficient of 0.86 in the cross-subject paradigm. Notably, it demonstrated an OAcc of 88.24% and a Cohen kappa coefficient of 0.80 in the leave-few-days-out analysis. Our MTCNN model also outperformed the existing deep learning models in sleep stage classification even when it was trained with only 16% of the total EEG data, achieving an OAcc of 85.62% and a Cohen kappa coefficient of 0.75 on the remaining 84% of testing data.The proposed MTCNN enables model explainability and it can be trained with lesser amount of data, which is beneficial to its application in the real-world because large amounts of training data are not often and readily available.
人类一生中的很大一部分时间都在睡眠中度过（睡眠是身体新陈代谢的重要驱动因素）。此外，由于睡眠剥夺可能导致各种健康问题，因此开发一种自动睡眠阶段检测模型以简化繁琐的人工标注过程至关重要。值得注意的是，最近提出的睡眠分期算法缺乏模型可解释性，并且仍需要提高性能。我们实现了多尺度神经生理学模拟内核，以捕捉不同频率和时间长度的与睡眠相关的脑电图（EEG）活动；所实现的模型被命名为“多尺度时间卷积神经网络（MTCNN）”。此外，我们使用一个开源数据集（包含153天多导睡眠图数据的Sleep-EDF数据库扩展版）评估了其性能。通过研究学习到的内核权重，我们观察到MTCNN检测到了每个睡眠阶段特有的EEG活动，如频率、K复合波和锯齿波。此外，在跨受试者范式中，关于这些具有神经生理学意义的特征的表征，MTCNN的总体准确率（OAcc）为91.12%，科恩kappa系数为0.86。值得注意的是，在留出几天的分析中，它的OAcc为88.24%，科恩kappa系数为0.80。即使仅使用总EEG数据的16%进行训练，我们的MTCNN模型在睡眠阶段分类方面也优于现有的深度学习模型，在其余84%的测试数据上实现了85.62%的OAcc和0.75的科恩kappa系数。所提出的MTCNN实现了模型可解释性，并且可以用较少的数据进行训练，这有利于其在现实世界中的应用，因为大量的训练数据并不经常且容易获得。
