EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Sleep Stage Classification During CPAP Therapy from CPAP-Airflow and Wearable Fingertip Signals

Hsin-Yu Chen iD, Aatif Husain iD, Andrey V Zinchuk, Henry K Yaggi, Muneeb Ahsan, Cheng-Yao Chen, Shirah Pokusa, Hau-Tieng Wu iD

Sensors · 11.06.2026 · 26 (12) · 3720

DOI: 10.3390/s26123720 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 11.06.2026. Verfasst von Hsin-Yu Chen und 7 weiteren Autor:innen. Beteiligte Einrichtung: PranaQ Pte. Ltd., Singapore 018937, Singapore. Hauptthemen laut MEDLINE: Sleep Stages, Continuous Positive Airway Pressure, Wearable Electronic Devices. Die Arbeit nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Continuous Positive Airway Pressure (CPAP) therapy is the standard treatment for obstructive sleep apnea–hypopnea syndrome (OSAHS), and photoplethysmography (PPG) sensors are commonly used in wearable devices for home sleep apnea testing. The recorded airflow and PPG signals from both sensors capture rich physiological patterns. We hypothesize that by combining information from these signals, we can efficiently estimate sleep dynamics of patients receiving CPAP treatment.

Methods

The airflow signals were obtained from CPAP titration devices, denoted as CPAP-airflow, while the PPG signals were collected using the PranaQ TipTraQ (TTQ001), a fingertip-worn wearable device. We separately trained one-dimensional convolutional neural networks for CPAP-airflow and PPG signals and fused their outputs through probabilistic ensembling to predict sleep stages. The ensemble method is a late-fusion soft-voting scheme that computes a linearly weighted combination of synchronized softmax probability vectors from the modality-specific models.

Results

For three-stage classification (Wake, REM, NREM), the PPG-based and CPAP-airflow-based models achieved overall Cohen’s kappa scores of 0.511 and 0.452, respectively, while the ensembled model improved the overall kappa to 0.587. The F1-score for the REM stage improved to 0.706 using the ensemble method, compared to 0.685 and 0.532 achieved by the individual models, respectively. In the four-stage classification (Wake, REM, Light, Deep) task, a deep sleep sensitivity of 0.596 was attained through the application of probabilistic ensembling.

Conclusions

A fusion scheme of complementary information from the CPAP and PPG enhances the accuracy of sleep stage detection and hence enables more precise sleep monitoring, especially with an improved REM identification. Clinical implications include applying the proposed algorithm to improve in-home auto-CPAP titration by capturing REM-related respiratory instability and avoiding under-titration in REM-dominant OSAHS, better reflecting the patient’s true nocturnal respiratory needs.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Sleep StagesContinuous Positive Airway PressureWearable Electronic DevicesHumansPhotoplethysmographySleep Apnea, ObstructiveFingersSignal Processing, Computer-AssistedPolysomnographyAlgorithmsFemaleMaleConvolutional Neural Networks

Stichwörter der Autor:innen

continuous positive airway pressureconvolutional neural networkdeep learninghome sleep monitoringphotoplethysmographyprobabilistic ensemblingsleep stage classification

Autor:innen und Institutionen

  • PranaQ Pte. Ltd., Singapore 018937, Singapore.
  • Department of Neurology, Duke University Medical Center, Durham, NC 27704, USA.
  • Department of Medicine, Yale University School of Medicine, New Haven, CT 06510, USA.
  • PranaQ, Co., New York, NY 10004, USA.
  • Courant Institute of Mathematical Sciences, New York University, New York, NY 10012, USA.

ORCID-Profile: Hsin-Yu Chen, Aatif Husain, Hau-Tieng Wu

Zitieren

APA

Chen, H. Y., Husain, A., Zinchuk, A. V., Yaggi, H. K., Ahsan, M., Chen, C. Y., Pokusa, S., & Wu, H. T. (2026). Sleep Stage Classification During CPAP Therapy from CPAP-Airflow and Wearable Fingertip Signals. Sensors, 26(12), 3720. https://doi.org/10.3390/s26123720

Vancouver

Chen HY, Husain A, Zinchuk AV, Yaggi HK, Ahsan M, Chen CY, et al. Sleep Stage Classification During CPAP Therapy from CPAP-Airflow and Wearable Fingertip Signals. Sensors. 2026;26(12):3720. doi:10.3390/s26123720

BibTeX
@article{Chen2026,
  author = {Chen, Hsin-Yu and Husain, Aatif and Zinchuk, Andrey V and Yaggi, Henry K and Ahsan, Muneeb and Chen, Cheng-Yao and Pokusa, Shirah and Wu, Hau-Tieng},
  title = {Sleep Stage Classification During CPAP Therapy from CPAP-Airflow and Wearable Fingertip Signals},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {12},
  pages = {3720},
  doi = {10.3390/s26123720}
}
Kostenlos starten →