SleepStageNet: A Lightweight and Explainable Deep Learning Architecture for Multi-Channel Sleep Staging

Background/Objectives: Automatic sleep staging from polysomnography (PSG) is particularly challenging in clinical cohorts with neurological disorders. Methods: This study presents SleepStageNet, a compact model (1.075M parameters) that integrates a dual-branch convolutional epoch encoder, feature gating, a bidirectional gated recurrent unit, and multi-head self-attention for five-class staging from five PSG channels (C3, C4, EOG1, EOG2, and chin EMG). The individual operations are adapted from established architectures; the study contribution is their compact integration and controlled evaluation in an Indian acute stroke cohort. Results: Of the 100 recordings in the Indian Sleep Polysomnography (iSLEEPS) resource, 95 satisfied the five-channel extraction criteria, yielding 78,323 annotated epochs. Subject-independent 10-fold stratified group cross-validation produced an accuracy of 73.91 ± 2.24%, a macro F1-score of 67.29 ± 1.96%, and a Cohen's κ of 0.634±0.029 (sample standard deviations). A matched single-branch encoder obtained κ=0.635 (full minus single branch: Δκ=-0.001, Holm-adjusted p=0.846), while matched C4-only input obtained κ=0.600 (full minus C4-only: Δκ=0.033, Holm-adjusted p=0.008). Grad-CAM and temporal attention visualizations provided qualitative evidence of physiologically plausible focus, while channel occlusion quantified the contribution of each signal. Without fine-tuning, a 10-model ensemble obtained κ=0.614 on ISRUC-SLEEP Subgroup III (10 healthy subjects; 8889 epochs). Conclusions: These results establish a reproducible reference for this clinical cohort while identifying the need for broader external and prospective validation.