Generalizable Deep Learning-based Sleep Staging Approach for Ambulatory Textile Electrode Headband Recordings.

Reliable, automated, and user-friendly solutions for the identification of sleep stages in home environment are needed in various clinical and scientific research settings. Previously we have shown that signals recorded with an easily applicable textile electrode headband (FocusBand, T 2 Green Pty Ltd) contain characteristics similar to the standard electrooculography (EOG, E1-M2). We hypothesize that the electroencephalographic (EEG) signals recorded using the textile electrode headband are similar enough with standard EOG in order to develop an automatic neural network-based sleep staging method that generalizes from diagnostic polysomnographic (PSG) data to ambulatory sleep recordings of textile electrode-based forehead EEG. Standard EOG signals together with manually annotated sleep stages from clinical PSG dataset (n = 876) were used to train, validate, and test a fully convolutional neural network (CNN). Furthermore, ambulatory sleep recordings including a standard set of gel-based electrodes and the textile electrode headband were conducted for 10 healthy volunteers at their homes to test the generalizability of the model. In the test set (n = 88) of the clinical dataset, the model's accuracy for 5-stage sleep stage classification was 80% (κ = 0.73) using only the single-channel EOG. The model generalized well for the headband-data, reaching 82% (κ = 0.75) overall sleep staging accuracy. In comparison, accuracy of the model was 87% (κ = 0.82) in home recordings using the standard EOG. In conclusion, the CNN model shows potential on automatic sleep staging of healthy individuals using a reusable electrode headband in a home environment.