Xu Ziliang, Zhu Yuanqiang, Zhao Hongliang, Guo Fan, Wang Huaning, Zheng Minwen
Department of Radiology, Xijing Hospital, Fourth Military Medical University, Xi'an, Shaanxi, 710032, People's Republic of China.
Department of Psychiatry, Xijing Hospital, Fourth Military Medical University, Xi'an, Shaanxi, 710032, People's Republic of China.
Nat Sci Sleep. 2022 May 24;14:995-1007. doi: 10.2147/NSS.S355702. eCollection 2022.
To investigate the general sleep stage classification performance of deep learning networks, three datasets, across different age groups, mental health conditions, and acquisition devices, comprising adults (SHHS) and children without mental health conditions (CCSHS), and subjects with mental health conditions (XJ), were included in this study.
A long short-term memory (LSTM) network was used to evaluate the effect of different ages, mental health conditions, and acquisition devices on the sleep stage classification performance and the general performance.
Results showed that the age and different mental health conditions may affect the sleep stage classification performance of the network. The same acquisition device using different parameters may not have an obvious effect on the classification performance. When using a single dataset and two datasets for training, the network performed better only on the training dataset. When training was conducted with three datasets, the network performed well for all datasets with a Cohen's Kappa of 0.8192 and 0.8472 for the SHHS and CCSHS, respectively, but performed relatively worse (0.6491) for the XJ, which indicated the complexity effect of different mental health conditions on the sleep stage classification task. Moreover, the performance of the network trained using three datasets was similar for each dataset to that of the network trained using a single dataset and tested on the same dataset.
These results suggested that when more datasets across different age groups, mental health conditions, and acquisition devices (ie, more datasets with different feature distributions for each sleep stage) are used for training, the general performance of a deep learning network will be superior for sleep stage classification tasks with varied conditions.
为研究深度学习网络的一般睡眠阶段分类性能，本研究纳入了三个数据集，涵盖不同年龄组、心理健康状况和采集设备，包括成年人（睡眠心脏健康研究[SHHS]）、无心理健康问题的儿童（儿童综合睡眠健康研究[CCSHS]）以及有心理健康问题的受试者（XJ）。
使用长短期记忆（LSTM）网络来评估不同年龄、心理健康状况和采集设备对睡眠阶段分类性能及总体性能的影响。
结果表明，年龄和不同的心理健康状况可能会影响网络的睡眠阶段分类性能。使用不同参数的同一采集设备对分类性能可能没有明显影响。当使用单个数据集和两个数据集进行训练时，网络仅在训练数据集上表现较好。当使用三个数据集进行训练时，网络在所有数据集上均表现良好，SHHS和CCSHS的科恩卡方系数分别为0.8192和0.8472，但XJ的表现相对较差（0.6491），这表明不同心理健康状况对睡眠阶段分类任务的复杂影响。此外，使用三个数据集训练的网络在每个数据集上的性能与使用单个数据集训练并在同一数据集上测试的网络相似。
这些结果表明，当使用更多跨不同年龄组、心理健康状况和采集设备的数据集（即每个睡眠阶段具有不同特征分布的更多数据集）进行训练时，深度学习网络在各种条件下的睡眠阶段分类任务中的总体性能将更优。
