S4Sleep: Elucidating the design space of deep-learning-based sleep stage classification models
This work addresses the time-consuming and variable manual scoring of sleep stages for medical professionals, though it is incremental as it refines existing deep learning approaches.
The study tackled the problem of automating sleep stage classification from polysomnography by systematically exploring design choices in encoder-predictor architectures, resulting in statistically significant performance improvements over state-of-the-art methods on the Sleep Heart Health Study dataset.
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 and achieve statistically significant performance improvements compared to state-of-the-art approaches on the extensive Sleep Heart Health Study dataset. We anticipate that the architectural insights gained from this study along with the refined methodology for architecture search demonstrated herein will not only prove valuable for future research in sleep staging but also hold relevance for other time series annotation tasks.