重新思考基于光体积描记（PPG）的睡眠分期：数据集、指标与基准

中文摘要 AI 辅助

自动睡眠分期会为夜间记录中连续的时间 epoch 分配离散的分期标签；传统上每个窗口至少跨越 30 秒，这反映了临床评分标准的最低时间分辨率。可穿戴光体积描记（PPG）作为基于实验室多导睡眠图（PSG）的非卧床替代方案，已受到持续关注，PSG 依赖脑电图（EEG）及其他记录模态，这些模态在临床环境外并不实用。然而，基于 PPG 的分期方法与基于 EEG 的方法相比仍存在显著差距，我们认为这种差距主要反映了信号与任务之间的不匹配。在稳定的分期内，PPG 的分期间特征差异比 EEG 更细微；但在分期边界处，PPG 的主要心血管特征——心率变异性和脉搏形态——会在几秒内急剧变化。因此，为每个 30 秒 epoch 分配一个标签的传统做法会抑制集中在边界附近的特征。我们通过两个步骤解决这一差距：首先，我们开发了一个基于隐半马尔可夫模型（HSMM）的标签扩展流程，将粗粒度的 epoch 标签转换为秒级注释。为评估这些扩展标签是否足够可靠以用于下游监督，我们在一个独立的专家审查数据集上对其进行验证，并通过一个辅助的睡眠-觉醒任务进行验证，该任务的标签独立于扩展流程。其次，我们在 MESA 数据集上使用得到的秒级监督，在四个架构多样的基准模型上，相较于原始 epoch 标签，将传统的四类 epoch 级分期的准确率提高了 3.7 至 5.7 个百分点；在 CFS 上的补充零样本评估显示，在队列和注释协议发生变化的情况下，迁移效益依然存在。

英文摘要

Automated sleep staging assigns discrete stage labels to successive time epochs throughout an overnight recording; conventionally each window spans at least 30 seconds, reflecting the minimum temporal resolution of the clinical scoring standard. Wearable photoplethysmography (PPG) has attracted sustained interest as an ambulatory alternative to laboratory-based polysomnography, which relies on electroencephalography (EEG) and other recording modalities that are impractical outside clinical environments. Yet PPG-based staging trails EEG-based methods by a substantial margin, and we argue this gap largely reflects a mismatch between signal and task. Within a stable stage, PPG's inter-stage feature differences are more subtle than those in EEG; yet at stage boundaries, PPG's principal cardiovascular features, heart rate variability and pulse morphology, shift sharply within seconds. The conventional practice of assigning one label to each 30-second epoch therefore suppresses feature that is concentrated near boundaries. We address this gap in two steps. First, we develop a label expansion pipeline based on Hidden Semi-Markov Models that converts coarse epoch labels into sec-level annotations. To assess whether these expanded labels are reliable enough for downstream supervision, we validate them on a separate expert-reviewed dataset and through an auxiliary sleep-wake task whose labels are independent of the expansion pipeline. Second, we use the resulting sec-level supervision on MESA to improve conventional four-class epoch-level staging across four architecturally diverse baselines by 3.7--5.7\,pp in accuracy against the original epoch labels, with supplementary zero-shot evaluation on CFS showing that the transfer benefit persists under cohort and annotation-protocol shift.

发表机构

• The University of Warwick（华威大学）
• Huashan Hospital, Fudan University（复旦大学附属华山医院）
• Human Phenome Institute, Fudan University（复旦大学人类表型组研究院）

机构由 AI 辅助整理，请以论文原文为准。