EUVIMEDEUVIMED entdecken
Crossref

Towards long-term sleep staging via wearable reflective photoplethysmography

Loris Constantin, Christian M Horvath iD, Florent Baty, Clémentine Aguet, Jérôme Van Zaen, Alia Lemkaddem, Loïc Jeanningros, Martin Proença, Xiaoli Yang, Kurt De Jaegere, Sebastian R Ott, João Jorge und 8 weitere

SLEEPJ · 2025

DOI: 10.1093/sleep/zsaf246 ↗

Kurz gefasst

Fachartikel in der Zeitschrift SLEEPJ, 2025. Verfasst von Loris Constantin und 19 weiteren Autor:innen. Beteiligte Einrichtung: Swiss Center of Electronics and Microtechnology (CSEM), MedTech, Neuchâtel, Switzerland. Hauptthemen laut MEDLINE: Photoplethysmography, Wearable Electronic Devices, Sleep Stages. Die Arbeit nennt 42 Literaturangaben. Gefördert von: Swiss National Science Foundation: ApneaSense project, Swiss National Science Foundation: ENHEART project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Study objectives Sleep staging is usually performed by manual scoring of polysomnography (PSG), which is expensive, laborious, and poorly scalable. We propose an alternative to PSG for ambulatory sleep staging using wearable photoplethysmography (PPG) recorded by a smartwatch and automated scoring.

Methods

We previously trained a deep learning model on public datasets, with the specific purpose of performance generalizability to unseen datasets. In the present work, the model was assessed on two datasets of reflective PPG collected from wrist-worn devices: (1) 68 overnight recordings and (2) for the first time, 493 long-term recordings each lasting for 24 hours (170 subjects). Findings were compared either to (1) expert scored sleep stages from PSG for the night recordings or (2) actigraphy for the long-term recordings.

Results

For the overnight recordings, the PPG-based model achieved 78.7% accuracy and a Cohen’s κ of 0.68 on reflective PPG collected using wrist-worn devices compared to PSG using a 4-class setup (wake, N1, and N2 combined, N3 and REM), and a sleep/wake accuracy of 94.1%, with a Cohen’s κ of 0.71. For the long-term recordings, a sleep/wake accuracy of 92.5% with a Cohen’s κ of 0.80 was achieved when compared to a state-of-the-art actigraphy-based deep learning model.

Conclusions

This state-of-the-art accuracy achieved on wrist-worn devices represents a significant advancement for home sleep monitoring and a valuable alternative to PSG-based sleep staging. Additionally, our model demonstrated promising results on long-term ambulatory recordings, paving the way towards continuous ambulatory monitoring of sleep stages and sleep–wake cycles. Statement of Significance Sleep staging is crucial to diagnose sleep disorders, but traditional methods are laborious and costly. We developed a sleep staging model that demonstrates high performance and exceptional generalization to unseen datasets, including those from wrist-worn devices, thereby possibly enabling accurate sleep staging from wearable technology. Furthermore, we evaluated the model's performance on 24-hour recordings of subjects of various health conditions, offering valuable insights for clinical applications and future research. These advancements significantly enhance the feasibility of continuous sleep monitoring at home, a low-cost, scalable, and comfortable alternative to current methods.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

PhotoplethysmographyWearable Electronic DevicesSleep StagesHumansPolysomnographyMaleFemaleActigraphyAdultMiddle AgedDeep Learning

Stichwörter der Autor:innen

ambulatorycardiac arrhythmiasdeep learningphotoplethysmographysleep stagingwearable device

Autor:innen und Institutionen

  • Swiss Center of Electronics and Microtechnology (CSEM), MedTech, Neuchâtel, Switzerland.
  • Department of Pulmonary Medicine, Allergology and Clinical Immunology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland.
  • Lung Center, HOCH Health Ostschweiz, Kantonsspital St.Gallen, St.Gallen, Switzerland.
  • Swiss Federal Institute of Technology, Lausanne, Vaud, Switzerland.
  • Department of Pneumology, St. Claraspital, Basel, Switzerland.
  • Department of Cardiology and Biomedical Research, University Hospital Bern, University of Bern, Bern, Switzerland.

ORCID-Profile: Christian M Horvath, Hildegard Tanner, Emrush Rexhaj, Fabian Braun

Förderung

  • Swiss National Science Foundation: ApneaSense project
  • Swiss National Science Foundation: ENHEART project

Zitieren

APA

Constantin, L., Horvath, C. M., Baty, F., Aguet, C., Van Zaen, J., Lemkaddem, A., Jeanningros, L., Proença, M., Yang, X., De Jaegere, K., Ott, S. R., Jorge, J., Thiran, J. P., Meister, T. A., Soria, R., Tanner, H., Rexhaj, E., Lemay, M., Brill, A. K., & Braun, F. (2025). Towards long-term sleep staging via wearable reflective photoplethysmography. SLEEPJ. https://doi.org/10.1093/sleep/zsaf246

Vancouver

Constantin L, Horvath CM, Baty F, Aguet C, Van Zaen J, Lemkaddem A, et al. Towards long-term sleep staging via wearable reflective photoplethysmography. SLEEPJ. 2025. doi:10.1093/sleep/zsaf246

BibTeX
@article{Constantin2025,
  author = {Constantin, Loris and Horvath, Christian M and Baty, Florent and Aguet, Clémentine and Van Zaen, Jérôme and Lemkaddem, Alia and Jeanningros, Loïc and Proença, Martin and Yang, Xiaoli and De Jaegere, Kurt and Ott, Sebastian R and Jorge, João and Thiran, Jean-Philippe and Meister, Theo A and Soria, Rodrigo and Tanner, Hildegard and Rexhaj, Emrush and Lemay, Mathieu and Brill, Anne-Kathrin and Braun, Fabian},
  title = {Towards long-term sleep staging via wearable reflective photoplethysmography},
  journal = {SLEEPJ},
  year = {2025},
  doi = {10.1093/sleep/zsaf246}
}
Kostenlos starten →