Paperdoi:10.1038/s41598-020-69935-7
Wearable monitoring of sleep-disordered breathing: estimation of the apnea–hypopnea index using wrist-worn reflective photoplethysmography
Sci. Rep. 2020;10:13512
TL;DR
A deep-learning model estimates the apnea-hypopnea index from wrist-worn reflective PPG alone, using cardiorespiratory and sleep information. It was trained on 250 recordings and tested on 188 independent clinical recordings: correlation 0.61 with PSG AHI, error 3±10 events/h, severity weighted κ 0.51, and OSA screening ROC-AUC 0.84/0.86/0.85 for mild/moderate/severe.
- Form factor: wrist
- Independent test set; error 3±10 events/h; Philips co-author.
- Independent test set.
- Independent 188-recording test set.
Abstract
A large part of the worldwide population suffers from obstructive sleep apnea (OSA), a disorder impairing the restorative function of sleep and constituting a risk factor for several cardiovascular pathologies. The standard diagnostic metric to define OSA is the apnea–hypopnea index (AHI), typically obtained by manually annotating polysomnographic recordings. However, this clinical procedure cannot be employed for screening and for long-term monitoring of OSA due to its obtrusiveness and cost. Here, we propose an automatic unobtrusive AHI estimation method fully based on wrist-worn reflective photoplethysmography (rPPG), employing a deep learning model exploiting cardiorespiratory and sleep information extracted from the rPPG signal trained with 250 recordings. We tested our method with an independent set of 188 heterogeneously disordered clinical recordings and we found it estimates the AHI with a good agreement to the gold standard polysomnography reference (correlation = 0.61, estimation error = 3±10 events/h). The estimated AHI was shown to reliably assess OSA severity (weighted Cohen’s kappa = 0.51) and screen for OSA (ROC–AUC = 0.84/0.86/0.85 for mild/moderate/severe OSA). These findings suggest that wrist-worn rPPG measurements that can be implemented in wearables such as smartwatches, have the potential to complement standard OSA diagnostic techniques by allowing unobtrusive sleep and respiratory monitoring.
Verbatim from the publisher's DOI record (opens in a new tab) · Publisher licence: https://creativecommons.org/licenses/by/4.0
Results on ChatPPG leaderboards · 4
All leaderboards| Leaderboard | Method | Result | Rank |
|---|---|---|---|
| Kempenhaeghe clinical cohort AUROC (AHI ≥ 15)Sleep apnea (OSA) screening | Wrist rPPG deep modelCaveat: Independent test set. | 0.86AUROC, higher is better | Unranked |
| Kempenhaeghe clinical cohort AUROC (AHI ≥ 30)Sleep apnea (OSA) screening | Wrist rPPG deep modelCaveat: Independent 188-recording test set. | 0.85AUROC, higher is better | Unranked |
| Kempenhaeghe clinical cohort AUROC (AHI ≥ 5)Sleep apnea (OSA) screening | Wrist rPPG deep modelCaveat: Independent 188-recording test set. | 0.84AUROC, higher is better | Unranked |
| Kempenhaeghe clinical cohort Pearson rSleep apnea (OSA) screening | Wrist rPPG deep modelCaveat: Independent test set; error 3±10 events/h; Philips co-author. | 0.61Pearson r, higher is better | Unranked |
4 rows are credited to this paper. Ranks apply within each leaderboard only, as reported by the source.
Tasks & signals
Tasks
Signals
Keywords
How it works
Cite this paper
Papini, G. B., Fonseca, P. M., van Gilst, M. M., Bergmans, J. W. M., Vullings, R., & Overeem, S. (2020). Wearable monitoring of sleep-disordered breathing: estimation of the apnea–hypopnea index using wrist-worn reflective photoplethysmography. Sci. Rep. 2020, 10, 13512. https://doi.org/10.1038/s41598-020-69935-7
Papini, Gabriele B., Pedro Miguel Fonseca, Merel M. van Gilst, Jan W. M. Bergmans, Rik Vullings, and Sebastiaan Overeem. 2020. "Wearable monitoring of sleep-disordered breathing: estimation of the apnea–hypopnea index using wrist-worn reflective photoplethysmography." Sci. Rep. 2020 10: 13512. https://doi.org/10.1038/s41598-020-69935-7.
Papini, G. B., Fonseca, P. M., van Gilst, M. M., Bergmans, J. W. M., Vullings, R. and Overeem, S. (2020) 'Wearable monitoring of sleep-disordered breathing: estimation of the apnea–hypopnea index using wrist-worn reflective photoplethysmography', Sci. Rep. 2020, 10, p. 13512. doi: 10.1038/s41598-020-69935-7.
Papini, Gabriele B., et al. "Wearable monitoring of sleep-disordered breathing: estimation of the apnea–hypopnea index using wrist-worn reflective photoplethysmography." Sci. Rep. 2020, vol. 10, 2020, p. 13512. https://doi.org/10.1038/s41598-020-69935-7.
G. B. Papini, P. M. Fonseca, M. M. van Gilst, J. W. M. Bergmans, R. Vullings, and S. Overeem, "Wearable monitoring of sleep-disordered breathing: estimation of the apnea–hypopnea index using wrist-worn reflective photoplethysmography," Sci. Rep. 2020, vol. 10, p. 13512, 2020, doi: 10.1038/s41598-020-69935-7.
@article{papini2020wearable,
title = {{Wearable monitoring of sleep-disordered breathing: estimation of the apnea–hypopnea index using wrist-worn reflective photoplethysmography}},
author = {Papini, Gabriele B. and Fonseca, Pedro Miguel and van Gilst, Merel M. and Bergmans, Jan W. M. and Vullings, Rik and Overeem, Sebastiaan},
year = {2020},
journal = {Sci. Rep. 2020},
volume = {10},
pages = {13512},
doi = {10.1038/s41598-020-69935-7}
}Added to the ChatPPG research hub
