← 研踪 PaperTrailarXiv:2611.21040 · v1
Towards wearable-scale, transition-aware sleep staging for clinical populations
首次提交 2026-11-16 20:57
版本更新 2026-11-16 20:57
雷达观测 2026-11-17 17:11
摘要
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.
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-16 20:57 · 最新观测版本
Towards wearable-scale, transition-aware sleep staging for clinical populations
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.
查看此版本解读 →查看此版本原文 ↗