Wang Xuhui, Zhu Yuanyuan
School of Computer Science, Wuhan University, Wuhan, 430061, China.
School of Computer Science, Wuhan University, Wuhan, 430061, China.
Comput Methods Programs Biomed. 2024 Dec;257:108405. doi: 10.1016/j.cmpb.2024.108405. Epub 2024 Sep 2.
Automatic sleep staging is essential for assessing and diagnosing sleep disorders, serving millions of people who suffer from them. Numerous sleep staging models have been proposed recently, but most of them have not fully explored the sleep transition rules that are essential for sleep experts to identify sleep stages. Therefore, one objective of this paper is to develop an automatic sleep staging model to capture the transition rules between sleep stages.
In this paper, we propose a novel sleep staging model named SleepGCN. It utilizes the deep features of electroencephalogram (EEG) and electrooculogram (EOG) signals extracted by the sleep representation learning (SRL) module, in conjunction with the transition rules learned by the sleep transition rule learning (STRL) module to identify sleep stages. Specifically, the SRL module utilizes the residual network (ResNet) and Long Short Term Memory (LSTM) structure to capture the deep time-invariant features and temporal information of each sleep stage from the two-channel EEG-EOG, and then applies a feature enhancement block to obtain the refined features. The STRL module employs a Graph Convolutional Network (GCN) and a transition rule matrix to capture transition rules between sleep stages based on the sequence labels of the input signals.
We evaluate SleepGCN on five public datasets: SleepEDF-20, SleepEDF-78, SHHS, DOD-H and DOD-O. Overall, SleepGCN achieves an accuracy of 89.70%, 87.70%, 86.16%, 82.07%, and 81.20%, alongside a macro-average F1-score of 85.20%, 82.70%, 77.69%, 72.44%, and 72.93% across these datasets, respectively.
The results achieved by our proposed model are much better than those of all other compared models. The ablation study validates the contributions of the SRL and STRL modules proposed in SleepGCN to the sleep staging tasks. Additionally, it shows that the sleep staging model using two-channel EEG-EOG outperforms the model using single-channel EEG or EOG. Overall, SleepGCN is an effective solution for sleep staging using two-channel EEG-EOG.
自动睡眠分期对于评估和诊断睡眠障碍至关重要，能为数百万受睡眠障碍困扰的人提供帮助。最近已经提出了许多睡眠分期模型，但其中大多数尚未充分探索睡眠转换规则，而这些规则对于睡眠专家识别睡眠阶段至关重要。因此，本文的一个目标是开发一种自动睡眠分期模型，以捕捉睡眠阶段之间的转换规则。
在本文中，我们提出了一种名为SleepGCN的新型睡眠分期模型。它利用睡眠表征学习（SRL）模块提取的脑电图（EEG）和眼电图（EOG）信号的深度特征，结合睡眠转换规则学习（STRL）模块学习到的转换规则来识别睡眠阶段。具体而言，SRL模块利用残差网络（ResNet）和长短期记忆（LSTM）结构从两通道EEG-EOG中捕捉每个睡眠阶段的深度时不变特征和时间信息，然后应用特征增强块来获得细化特征。STRL模块采用图卷积网络（GCN）和转换规则矩阵，基于输入信号的序列标签捕捉睡眠阶段之间的转换规则。
我们在五个公共数据集上评估了SleepGCN：SleepEDF-20、SleepEDF-78、SHHS、DOD-H和DOD-O。总体而言，SleepGCN在这些数据集上分别实现了89.70%、87.70%、86.16%、82.07%和81.20%的准确率，以及85.20%、82.70%、77.69%、72.44%和72.93%的宏平均F1分数。
我们提出的模型所取得的结果比所有其他比较模型都要好得多。消融研究验证了SleepGCN中提出的SRL和STRL模块对睡眠分期任务的贡献。此外，它表明使用两通道EEG-EOG的睡眠分期模型优于使用单通道EEG或EOG的模型。总体而言，SleepGCN是一种使用两通道EEG-EOG进行睡眠分期的有效解决方案。
