Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Combining scEEG and PPG for reliable sleep staging using lightweight wearables

Jiawei Wang, Liang Xu, Shuntian Zheng, Yu Guan, Kaichen Wang, Ziqing Zhang, Chen Chen, Laurence T. Yang, Sai Gu

TL;DR

The findings suggest that scEEG-PPG fusion is a promising approach for lightweight wearable based sleep monitoring, offering a pathway toward more accessible sleep health assessment.

Abstract

Reliable sleep staging remains challenging for lightweight wearable devices such as single-channel electroencephalography (scEEG) or photoplethysmography (PPG). scEEG offers direct measurement of cortical activity and serves as the foundation for sleep staging, yet exhibits limited performance on light sleep stages. PPG provides a low-cost complement that captures autonomic signatures effective for detecting light sleep. However, prior PPG-based methods rely on full night recordings (8 - 10 hours) as input context, which is less practical to provide timely feedback for sleep intervention. In this work, we investigate scEEG-PPG fusion for 4-class sleep staging under short-window (30 s - 30 min) constraints. First, we evaluate the temporal context required for each modality, to better understand the relationship of sleep staging performance with respect to monitoring window. Second, we investigate three fusion strategies: score-level fusion, cross-attention fusion enabling feature-level interactions, and Mamba-enhanced fusion incorporating temporal context modeling. Third, we train and evaluate on the Multi-Ethnic Study of Atherosclerosis (MESA) dataset and perform cross-dataset validation on the Cleveland Family Study (CFS) and the Apnea, Bariatric surgery, and CPAP (ABC) datasets. The Mamba-enhanced fusion achieves the best performance on MESA (Cohen's Kappa $κ$ = 0.798, Acc = 86.9%), with particularly notable improvement in light sleep classification (F1-score: 85.63% vs. 77.76%, recall: 82.85% vs. 69.95% for scEEG alone), and generalizes well to CFS and ABC datasets with different populations. These findings suggest that scEEG-PPG fusion is a promising approach for lightweight wearable based sleep monitoring, offering a pathway toward more accessible sleep health assessment. Source code of this project can be found at: https://github.com/DavyWJW/scEEG-PPGFusion

Combining scEEG and PPG for reliable sleep staging using lightweight wearables

TL;DR

The findings suggest that scEEG-PPG fusion is a promising approach for lightweight wearable based sleep monitoring, offering a pathway toward more accessible sleep health assessment.

Abstract

Reliable sleep staging remains challenging for lightweight wearable devices such as single-channel electroencephalography (scEEG) or photoplethysmography (PPG). scEEG offers direct measurement of cortical activity and serves as the foundation for sleep staging, yet exhibits limited performance on light sleep stages. PPG provides a low-cost complement that captures autonomic signatures effective for detecting light sleep. However, prior PPG-based methods rely on full night recordings (8 - 10 hours) as input context, which is less practical to provide timely feedback for sleep intervention. In this work, we investigate scEEG-PPG fusion for 4-class sleep staging under short-window (30 s - 30 min) constraints. First, we evaluate the temporal context required for each modality, to better understand the relationship of sleep staging performance with respect to monitoring window. Second, we investigate three fusion strategies: score-level fusion, cross-attention fusion enabling feature-level interactions, and Mamba-enhanced fusion incorporating temporal context modeling. Third, we train and evaluate on the Multi-Ethnic Study of Atherosclerosis (MESA) dataset and perform cross-dataset validation on the Cleveland Family Study (CFS) and the Apnea, Bariatric surgery, and CPAP (ABC) datasets. The Mamba-enhanced fusion achieves the best performance on MESA (Cohen's Kappa = 0.798, Acc = 86.9%), with particularly notable improvement in light sleep classification (F1-score: 85.63% vs. 77.76%, recall: 82.85% vs. 69.95% for scEEG alone), and generalizes well to CFS and ABC datasets with different populations. These findings suggest that scEEG-PPG fusion is a promising approach for lightweight wearable based sleep monitoring, offering a pathway toward more accessible sleep health assessment. Source code of this project can be found at: https://github.com/DavyWJW/scEEG-PPGFusion
Paper Structure (29 sections, 10 equations, 9 figures, 5 tables)

This paper contains 29 sections, 10 equations, 9 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Methodology
  3. Datasets
  4. MESA Dataset
  5. CFS Dataset
  6. ABC Dataset
  7. Signal Preprocessing
  8. scEEG Preprocessing
  9. PPG Preprocessing
  10. Model Architecture
  11. scEEG-based model
  12. PPG-based model
  13. scEEG-PPG fusion
  14. Evaluation Metrics
  15. Performance statistics
  16. ...and 14 more sections

Figures (9)

  • Figure 1: Wearable sleep monitoring devices and the motivation for scEEG-PPG fusion: (a) clinical gold-standard PSG wikipedia_polysomnography, (b) multi-signal system integrating EEG, EOG, and EMG (Tosoo AG) eicher2024phase, (c) multi-channel EEG system (Greentek GT Cap) greenteksensor_gtcap, (d) forehead scEEG device (Neurovista Sleep Monitor) Neurovista2024, (e) headset scEEG device (Brainlink Lite) abdal2025eeg, (f) PPG-based smart ring (RingConn) wang2024will, (g) PPG-based smart watch (Garmin) macdermott2019forensic.
  • Figure 2: Demographic characteristics of MESA, CFS and ABC datasets: (a) Age. (b) Sex distribution. (c) Racial composition highlighting MESA's ethnic diversity, CFS's predominantly Black and White population, and ABC's majority White cohort.
  • Figure 3: Architecture of baseline models: (a) scEEG model, (b) PPG model.
  • Figure 4: Overview of three fusion strategies: (a) score-level fusion, (b) cross-attention fusion, and (c) Mamba-enhanced fusion.
  • Figure 5: Confusion matrices for sleep stage classification across different window lengths using scEEG and PPG.
  • ...and 4 more figures