Automated Sleep Staging via Parallel Frequency-Cut Attention
This work addresses the problem of accurate and interpretable sleep stage classification for medical diagnostics, representing an incremental improvement with specific gains in performance.
The paper tackles automated sleep staging from EEG signals by proposing a framework that extracts time-frequency features and uses attention-based architecture to correlate them with sleep stages, achieving state-of-the-art F1 scores of 0.93, 0.88, and 0.87 for wake, N2, and N3 stages on the Sleep Heart Health Study dataset.
This paper proposes a novel framework for automatically capturing the time-frequency nature of electroencephalogram (EEG) signals of human sleep based on the authoritative sleep medicine guidance. The framework consists of two parts: the first part extracts informative features by partitioning the input EEG spectrograms into a sequence of time-frequency patches. The second part is constituted by an attention-based architecture to efficiently search for the correlation between partitioned time-frequency patches and defining factors of sleep stages in parallel. The proposed pipeline is validated on the Sleep Heart Health Study dataset with new state-of-the-art results for the stages wake, N2, and N3, obtaining respective F1 scores of 0.93, 0.88, and 0.87, with only EEG signals used. The proposed method also has a high inter-rater reliability of 0.80 kappa. We also visualize the correspondence between sleep staging decisions and features extracted by the proposed method, providing strong interpretability for our model.