cs.HCNov 16, 2026

Towards wearable-scale, transition-aware sleep staging for clinical populations

Authors: Suvadeep Maiti, Keya Sinha, Raju S. Bapi

Organizations: University College London, London, United Kingdom · IHub-Data, International Institute of Information Technology, Hyderabad, India · Indian Institute of Science Education and Research (IISER) Bhopal, India

Abstract

Automatic sleep staging models are predominantly developed on healthy sleepers and generalize poorly to clinical populations with fragmented sleep. Across three cohorts (patients with stroke, isolated REM sleep behaviour disorder, and other sleep disorders), we observe 2-3x more awakenings per hour, nearly twice as much N1, and less REM sleep than in healthy sleepers. We propose a label-efficient teacher-student framework for wearable-scale sleep staging. SleepGPT (136M parameters), adapted using labels from 25% of training patients, supervises a causal CNN-GRU (31k parameters; 122 KB) that stages EEG, EOG, or both in real time. We introduce Gcv-TAD, a new black-box transition-aware distillation loss. It emphasizes uncommon stage transitions while discounting those that vary across patients, using a prior estimated from labelled patients. In patient-wise 10-fold cross-validation, Gcv-TAD improves per-patient macro F1 over supervised training on the same labels by +3.2 to +7.6 points on average. Gains are largest on N1, and performance approaches full-label training.

Figures & tables

Explore similar work

CardsList
  1. StageGuard: Physiologically Constrained Sleep Staging

    Jul 25, 2026Juntang Wang, Yihan Wang, Hao Wu +3Constrained DecodingSleep Stage Classification

  2. Rethinking PPG-based Sleep Staging: Datasets, Metrics, and Benchmarks

    Aug 2, 2026Shuntian Zheng, Jiawei Wang, Cong Fu +4Sleep Stage ClassificationPhotoplethysmography

  3. SWINSleepNet: A Hierarchical Context-Aware Framework for Sleep Staging (v2)

    Aug 3, 2026Chongjian Wang, Junjie GaoSleep Stage ClassificationHybrid CNN-Transformer Architectures