DeepSleepNet: A Model for Automatic Sleep Stage Scoring Based on Raw Single-Channel EEG

TLDR

Existing sleep‑stage scoring methods largely depend on hand‑engineered features and rarely capture temporal transition rules. The study introduces DeepSleepNet, a deep‑learning model for automatic sleep‑stage scoring from raw single‑channel EEG. DeepSleepNet employs convolutional layers to extract time‑invariant features and a bidirectional LSTM to learn stage transition rules, trained via a two‑step algorithm and evaluated on multiple single‑channel EEGs from two public datasets. The model achieved overall accuracy and macro F1‑scores comparable to state‑of‑the‑art methods (e.g., 86.2%/81.7% on MASS and 82.0%/76.9% on Sleep‑EDF) and proved capable of learning features across diverse raw EEG channels and datasets without hand‑engineered features.

Abstract

The present study proposes a deep learning model, named DeepSleepNet, for automatic sleep stage scoring based on raw single-channel EEG. Most of the existing methods rely on hand-engineered features which require prior knowledge of sleep analysis. Only a few of them encode the temporal information such as transition rules, which is important for identifying the next sleep stages, into the extracted features. In the proposed model, we utilize Convolutional Neural Networks to extract time-invariant features, and bidirectional-Long Short-Term Memory to learn transition rules among sleep stages automatically from EEG epochs. We implement a two-step training algorithm to train our model efficiently. We evaluated our model using different single-channel EEGs (F4-EOG(Left), Fpz-Cz and Pz-Oz) from two public sleep datasets, that have different properties (e.g., sampling rate) and scoring standards (AASM and R&K). The results showed that our model achieved similar overall accuracy and macro F1-score (MASS: 86.2%-81.7, Sleep-EDF: 82.0%-76.9) compared to the state-of-the-art methods (MASS: 85.9%-80.5, Sleep-EDF: 78.9%-73.7) on both datasets. This demonstrated that, without changing the model architecture and the training algorithm, our model could automatically learn features for sleep stage scoring from different raw single-channel EEGs from different datasets without utilizing any hand-engineered features.