Purpose: 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.
Methods: 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: 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.
Conclusion: 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.
Keywords: sleep stage classification, deep learning network, electroencephalogram, time-frequency spectrum