Paperdoi:10.1038/s41598-026-73376-z

Multi-window HRV and temporal context for sleep staging from ECG and smartwatch PPG-derived intervals

Venue listed2026Added Nov 15, 2026

  • YW
  • YP
  • JL
  • ZZ
  • CC
  • YC
  • ZC
  • YZ
  • +2

Authors: Yimin Wang, Yiran Peng, Jiaqi Li, Ziyue Zhang, Chenxi Cao, Yujiao Chai, Zixiang Cai, Yu Zou, Zhangyan Yan, Zhulin Tao

Scientific Reports (2026-11-05)

TL;DR

HRV-centred 4-class sleep staging (Wake / Light / Deep / REM) from ECG RR intervals or smartwatch PPG-derived IBIs. Time, frequency and nonlinear HRV features over multiple temporal windows plus a sleep-progress context feature, integrated by a lightweight Transformer encoder. Accuracy / Cohen's kappa: 0.6988 / 0.5326 on an SHHS 1000-subject subset, 0.6958 / 0.4830 on Huami ECG, 0.6915 / 0.4615 on Huami smartwatch PPG.

  • Form factor: wrist (Huami smartwatch)

Abstract

Sleep staging is essential for evaluating sleep quality, yet conventional polysomnography is costly, intrusive, and difficult to deploy in everyday settings. This study presents an HRV-centered sleep-staging framework for ECG-derived RR intervals and smartwatch PPG-derived IBI sequences. Rather than introducing a new Transformer architecture, the study systematically evaluates multi-window HRV representation and sleep-progress context for four-class sleep staging, while examining demographic information and feature-interaction strategies as auxiliary components. The framework extracts time-domain, frequency-domain, and nonlinear HRV features from multiple temporal windows, combines them primarily with sleep-progress context while optionally incorporating demographic context, and uses a lightweight Transformer encoder as a temporal integration module for classifying Wake, Light sleep, Deep sleep, and REM sleep. In the final baseline comparison, the proposed configuration achieved accuracies and Cohen’s Kappa coefficients of 0.6988/0.5326 on the SHHS 1000 subset, 0.6958/0.4830 on Huami ECG, and 0.6915/0.4615 in the Huami smartwatch PPG setting. Ablation analyses showed that multi-window HRV representation and temporal sleep-progress information provided the most consistent contributions, whereas demographic variables and feature-interaction strategies had auxiliary and dataset-dependent effects. For practical interpretation, configurations without the future-context 300-s feature are considered the relevant setting because they exclude explicitly post-epoch information, whereas configurations containing this feature are treated only as offline retrospective analyses. Further validation across independent datasets, wearable devices, prospective deployment settings, and external PPG interval-estimation pipelines is needed before broader real-world use.

Verbatim from OpenAlex (opens in a new tab) · Abstract via OpenAlex (publisher-deposited); © the authors/publisher

Results on ChatPPG leaderboards

All leaderboards

No results from this paper on ChatPPG leaderboards yet. Browse the leaderboards.

Tasks & signals

Tasks

Sleep staging

Signals

Keywords

IBISleep Staging4 ClassSHHSHuamiTransformer

Datasets used

How it works

How Method works: Setup → Method → TargetSetup: Signals (PPG (IBI), ECG (RR)); Form factor (wrist (Huami smartwatch)). Method: Method (Transformer). Target: Sleep staging.SetupSignals: PPG (IBI), ECG (RR)SignalsPPG (IBI), ECG (RR)Form factor: wrist (Huami smartwatch)Form factorwrist (Huami smartwatch)Method×NMethodTransformerTargetSleep stagingSleep staging

Cite this paper

Cite this paper with the fields recorded here. Check it against the publisher before submitting.

Wang, Y., Peng, Y., Li, J., Zhang, Z., Cao, C., Chai, Y., Cai, Z., Zou, Y., Yan, Z., & Tao, Z. (2026). Multi-window HRV and temporal context for sleep staging from ECG and smartwatch PPG-derived intervals. Scientific Reports. https://doi.org/10.1038/s41598-026-73376-z
Wang, Yimin, Yiran Peng, Jiaqi Li, Ziyue Zhang, Chenxi Cao, Yujiao Chai, Zixiang Cai, Yu Zou, Zhangyan Yan, and Zhulin Tao. 2026. "Multi-window HRV and temporal context for sleep staging from ECG and smartwatch PPG-derived intervals." Scientific Reports. https://doi.org/10.1038/s41598-026-73376-z.
Wang, Y., Peng, Y., Li, J., Zhang, Z., Cao, C., Chai, Y., Cai, Z., Zou, Y., Yan, Z. and Tao, Z. (2026) 'Multi-window HRV and temporal context for sleep staging from ECG and smartwatch PPG-derived intervals', Scientific Reports. doi: 10.1038/s41598-026-73376-z.
Wang, Yimin, et al. "Multi-window HRV and temporal context for sleep staging from ECG and smartwatch PPG-derived intervals." Scientific Reports, 2026. https://doi.org/10.1038/s41598-026-73376-z.
Y. Wang et al., "Multi-window HRV and temporal context for sleep staging from ECG and smartwatch PPG-derived intervals," Scientific Reports, 2026, doi: 10.1038/s41598-026-73376-z.
@article{wang2026multiwindow,
  title         = {{Multi-window HRV and temporal context for sleep staging from ECG and smartwatch PPG-derived intervals}},
  author        = {Wang, Yimin and Peng, Yiran and Li, Jiaqi and Zhang, Ziyue and Cao, Chenxi and Chai, Yujiao and Cai, Zixiang and Zou, Yu and Yan, Zhangyan and Tao, Zhulin},
  year          = {2026},
  journal       = {Scientific Reports},
  doi           = {10.1038/s41598-026-73376-z}
}

Added to the ChatPPG research hub