Scoring sleep stages in polysomnography recordings is a time-consuming task plagued by significant inter-rater variability. Therefore, it stands to benefit from the application of machine learning algorithms. While many algorithms have been proposed for this purpose, certain critical architectural decisions have not received systematic exploration. In this study, we meticulously investigate these design choices within the broad category of encoder-predictor architectures. We identify robust architectures applicable to both time series and spectrogram input representations. These architectures incorporate structured state space models as integral components, leading to statistically significant advancements in performance on the extensive SHHS dataset. These improvements are assessed through both statistical and systematic error estimations. We anticipate that the architectural insights gained from this study will not only prove valuable for future research in sleep staging but also hold relevance for other time series annotation tasks.

通过研究编码器-预测器体系结构的设计选择，我们找到了适用于时间序列和频谱图输入表示的可靠体系结构，其中结构化状态空间模型作为其组成部分，从而在广泛的SHHS数据集上显著提高了性能，这些改进通过统计和系统误差估计进行了评估。我们预计，从本研究获得的体系结构见解不仅对于未来的睡眠分期研究有价值，而且对其他时间序列注释任务也具有相关性。

S4Sleep: 深度学习基于睡眠阶段分类模型的设计空间阐明