University Politehnica of Bucharest, Bucharest, Romania.
Onera Health, Eindhoven, The Netherlands.
Biomed Tech (Berl). 2022 Jun 6;67(4):267-281. doi: 10.1515/bmt-2021-0408. Print 2022 Aug 26.
Supervised automatic sleep scoring algorithms are usually trained using sleep stage labels manually annotated on 30 s epochs of PSG data. In this study, we investigate the impact of using shorter epochs with various PSG input signals for training and testing a Long Short Term Memory (LSTM) neural network. An LSTM model is evaluated on the provided 30 s epoch sleep stage labels from a publicly available dataset, as well as on 10 s subdivisions. Additionally, three independent scorers re-labeled a subset of the dataset on shorter time windows. The automatic sleep scoring experiments were repeated on the re-annotated subset.The highest performance is achieved on features extracted from 30 s epochs of a single channel frontal EEG. The resulting accuracy, precision and recall were of 92.22%, 67.58% and 66.00% respectively. When using a shorter epoch as input, the performance decreased by approximately 20%. Re-annotating a subset of the dataset on shorter time epochs did not improve the results and further altered the sleep stage detection performance. Our results show that our feature-based LSTM classification algorithm performs better on 30 s PSG epochs when compared to 10 s epochs used as input. Future work could be oriented to determining whether varying the epoch size improves classification outcomes for different types of classification algorithms.
监督式自动睡眠评分算法通常使用在 PSG 数据的 30 秒时段上手动标注的睡眠阶段标签进行训练。在这项研究中，我们研究了使用较短的时段以及各种 PSG 输入信号进行训练和测试长短期记忆 (LSTM) 神经网络的影响。我们使用来自公开数据集的 30 秒时段的睡眠阶段标签以及 10 秒细分对 LSTM 模型进行了评估。此外，三位独立的评分员在更短的时间窗口上重新标记了数据集的子集。自动睡眠评分实验在重新注释的子集中重复进行。从单个通道额部 EEG 的 30 秒时段中提取的特征实现了最高的性能。得到的准确率、精度和召回率分别为 92.22%、67.58%和 66.00%。当使用较短的时段作为输入时，性能下降了约 20%。在更短的时间窗口上重新注释数据集的子集并没有提高结果，反而进一步改变了睡眠阶段检测性能。我们的结果表明，与作为输入的 10 秒时段相比，我们基于特征的 LSTM 分类算法在 30 秒 PSG 时段上的表现更好。未来的工作可以确定是否改变时段大小可以改善不同类型的分类算法的分类结果。
