Automated Sleep Staging via Parallel Frequency-Cut Attention

Abstract

Stage-based sleep screening is a widely-used tool in both healthcare and neuroscientific research, as it allows for the accurate assessment of sleep patterns and stages. In this paper, we propose a novel framework that is based on authoritative guidance in sleep medicine and is designed to automatically capture the time-frequency characteristics of sleep electroencephalogram (EEG) signals in order to make staging decisions. Our framework consists of two main phases: a feature extraction process that partitions the input EEG spectrograms into a sequence of timefrequency patches, and a staging phase that searches for correlations between the extracted features and the defining characteristics of sleep stages. To model the staging phase, we utilize a Transformer model with an attentionbased module, which allows for the extraction of global contextual relevance among time-frequency patches and the use of this relevance for staging decisions. The proposed method is validated on the large-scale Sleep Heart Health Study dataset and achieves new state-of-the-art results for the wake, N2, and N3 stages, with respective F1 scores of 0.93, 0.88, and 0.87 using only EEG signals. Our method also demonstrates high inter-rater reliability, with a kappa score of 0.80. Moreover, we provide visualizations of the correspondence between sleep staging decisions and features extracted by our method, which enhances the interpretability of the proposal. Overall, our work represents a significant contribution to the field of automated sleep staging and has important implications for both healthcare and neuroscience research.

Advances in Modeling and Interpretability of Deep Neural Sleep Staging: A Systematic Review

“…Many authors [28,[45][46][47] preprocess the data by removing frequency components outside of the accepted ranges of brainwave activity. In EEG, this is usually performed with a Butterworth band-pass filter tuned to 0.4-30 Hz.…”

“…So far, we have explored models based on CNN and RNN architectures. There are many other papers that, in general, used these types of architecture, with subtle differences in their modeling through loss function and some prepossessing on the data [13,15,22,27,37,46,58,. In [68], the authors showed the power of multi-scale modeling to capture fast and slow varying features.…”

“…It is easy to see what factors contribute the most to the classification. This along with [46,122] are examples of verifiable and interpretable techniques. As presented, most of the interpretable approaches such as [24,108], which show significant insight on how the model perceives the data, can help the clinicians trust DNNs to be incorporated in clinics for sleep disorder detection.…”

Understanding the Role of Self-Attention in a Transformer Model for the Discrimination of SCD From MCI Using Resting-State EEG

“…In this context, the potential of explanations obtained from attention weights has been explored in the field of EEG classification. Recently, several works employing Transformers for EEG-based automatic sleep staging have highlighted the importance of understanding which physiologically interpretable patterns are detected by the model and how different parts of the input influence the classification outcome [33]- [35]. In particular, by mapping attention scores to the raw EEG signals, they all found that the Transformers attended more to sleep-related features, such as K-complexes and spindles, to classify specific sleep stages.…”