Automatic Sleep Stage Scoring with Single-Channel EEG Using Convolutional Neural Networks
About
We used convolutional neural networks (CNNs) for automatic sleep stage scoring based on single-channel electroencephalography (EEG) to learn task-specific filters for classification without using prior domain knowledge. We used an openly available dataset from 20 healthy young adults for evaluation and applied 20-fold cross-validation. We used class-balanced random sampling within the stochastic gradient descent (SGD) optimization of the CNN to avoid skewed performance in favor of the most represented sleep stages. We achieved high mean F1-score (81%, range 79-83%), mean accuracy across individual sleep stages (82%, range 80-84%) and overall accuracy (74%, range 71-76%) over all subjects. By analyzing and visualizing the filters that our CNN learns, we found that rules learned by the filters correspond to sleep scoring criteria in the American Academy of Sleep Medicine (AASM) manual that human experts follow. Our method's performance is balanced across classes and our results are comparable to state-of-the-art methods with hand-engineered features. We show that, without using prior domain knowledge, a CNN can automatically learn to distinguish among different normal sleep stages.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Sleep stage scoring | MASS (subject-wise) | Accuracy79.9 | 22 | |
| Sleep Stage Classification | Sleep-EDF | Accuracy84 | 16 | |
| Sleep stage scoring | Sleep-EDF Independent Training and Test Sets (subject-wise) | MF169.8 | 13 | |
| Sleep Stage Classification | DOD-H (test) | F1 Score0.751 | 9 | |
| Sleep Stage Classification | DOD-O (test) | Overall F1 Score79.1 | 9 | |
| Sleep Stage Classification | MASS (Montreal Archive of Sleep Studies) (SS3 only) | Overall Accuracy83 | 5 | |
| Sleep Stage Classification | Sleep Stage Classification (Overall) | Precision91 | 4 | |
| Sleep Staging | SHHS | Accuracy86.8 | 3 |