Enhancing Healthcare with EOG: A Novel Approach to Sleep Stage Classification

We introduce an innovative approach to automated sleep stage classification using electrooculogram (EOG) signals, addressing the discomfort and impracticality associated with electroencephalogram (EEG) data acquisition. In addition, this approach is untapped in the field, highlighting its potential for novel insights and contributions. Our proposed SE-Resnet-Transformer model effectively classifies five distinct sleep stages from raw EOG signals. Extensive validation on publicly available databases (SleepEDF-20, SleepEDF-78, and SHHS) reveals performance, with macro-F1 scores of 74.72, 70.63, and 69.26, respectively. The model excels in identifying Rapid Eye Movement (REM) sleep, a crucial aspect of sleep disorder investigations. We also provide insight into the internal mechanisms of the model using techniques such as GradCAM and t-SNE plots. Our method improves the accessibility of sleep stage classification while decreasing the need for EEG modalities. This development will have promising implications for healthcare and the incorporation of wearable technology into sleep studies, thereby advancing the field’s potential for enhanced diagnostics and patient comfort.