EUVIMEDEUVIMED entdecken
BeobachtungsstudieValidierungsstudie

Validation of a fingertip home sleep apnea testing system using deep learning AI and a temporal event localization analysis

Ke-Wei Chen, Chun-Hsien Tseng, Hsin-Chien Lee iD, Wen-Te Liu, Kun-Ta Chou, Hau-Tieng Wu iD

SLEEP · 12.05.2025 · 48 (5)

DOI: 10.1093/sleep/zsae317 ↗

Kurz gefasst

Beobachtungsstudie in der Zeitschrift SLEEP, online erschienen am 16.01.2025. Verfasst von Ke-Wei Chen und 5 weiteren Autor:innen. Beteiligte Einrichtung: PranaQ Pte. Ltd., Singapore. Hauptthemen laut MEDLINE: Deep Learning, Polysomnography, Sleep Apnea Syndromes, Sleep Apnea, Obstructive. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 37 Literaturangaben. Gefördert von: PranaQ Pte. Ltd..

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Study Objectives This paper validates TipTraQ, a compact home sleep apnea testing (HSAT) system. TipTraQ comprises a fingertip-worn device, a mobile application, and a cloud-based deep learning artificial intelligence (AI) system. The device utilizes photoplethysmography (red, infrared, and green channels) and accelerometer sensors to assess sleep apnea by the AI system.

Methods

We prospectively enrolled 240 participants suspected of obstructive sleep apnea (OSA) at a tertiary medical center for internal validation and 112 participants independently at another center for external validation. All participants underwent simultaneous polysomnography and TipTraQ HSAT. We compared TipTraQ-derived total sleep time (TQ-TST) and TipTraQ-derived Respiratory Events Index (TQ-REI) with expert-determined TST and apnea–hypopnea index (AHI), based on AASM standards with the 1B hypopnea rule. Temporal event localization analysis for respiratory event prediction was conducted at both event and hourly levels.

Results

In the external validation, the Spearman correlation coefficients for TQ-TST vs. TST and TQ-REI vs. AHI were 0.81 and 0.95, respectively. The root mean square error were 0.53 hours for TQ-TST vs. TST and 7.53 events/h for TQ-REI vs. AHI. For apnea/hypopnea prediction with a 10-second grace period, the true positive, false positive, and false negative rates in temporal event localization analysis were 0.76, 0.24, and 0.23, respectively. The four-way OSA severity classification achieved a Cohen’s kappa of 0.7.

Conclusions

TQ-TST and TQ-REI predict TST and AHI with comparable performance to existing devices of the same type, and respiratory event prediction is validated through temporal event localization analysis. Clinical Trials Development of TipTraQ Home Sleep Test, https://clinicaltrials.gov/study/NCT06474351?term=NCT06474351&rank=1, NCT06474351 TipTraQ Home Sleep Test Study, SHH, https://clinicaltrials.gov/study/NCT06633887?term=NCT06633887&rank=1, NCT06633887

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningPolysomnographySleep Apnea SyndromesSleep Apnea, ObstructiveAdultFemaleHumansMaleMiddle AgedAccelerometryMobile ApplicationsPhotoplethysmographyProspective StudiesReproducibility of Results

Stichwörter der Autor:innen

accelerometerdeep learning AI systemhome sleep apnea testingphotoplethysmogram

Autor:innen und Institutionen

  • PranaQ Pte. Ltd., Singapore.
  • Department of Chest Medicine, Taipei Veterans General Hospital, Taipei, Taiwan.
  • Graduate Institute of Humanities in Medicine, College of Humanities & Social Sciences, Taipei Medical University, Taipei, Taiwan.
  • Department of Psychiatry & Sleep Center, Taipei Medical University Hospital, Taipei, Taiwan.
  • Sleep Center, Shuang Ho Hospital, Taipei Medical University, New Taipei City, Taiwan.
  • School of Respiratory Therapy, College of Medicine, Taipei Medical University, Taipei, Taiwan.

ORCID-Profile: Hsin-Chien Lee, Hau-Tieng Wu

Förderung

  • PranaQ Pte. Ltd.

Zitieren

APA

Chen, K. W., Tseng, C. H., Lee, H. C., Liu, W. T., Chou, K. T., & Wu, H. T. (2025). Validation of a fingertip home sleep apnea testing system using deep learning AI and a temporal event localization analysis. SLEEP, 48(5). https://doi.org/10.1093/sleep/zsae317

Vancouver

Chen KW, Tseng CH, Lee HC, Liu WT, Chou KT, Wu HT. Validation of a fingertip home sleep apnea testing system using deep learning AI and a temporal event localization analysis. SLEEP. 2025;48(5). doi:10.1093/sleep/zsae317

BibTeX
@article{Chen2025,
  author = {Chen, Ke-Wei and Tseng, Chun-Hsien and Lee, Hsin-Chien and Liu, Wen-Te and Chou, Kun-Ta and Wu, Hau-Tieng},
  title = {Validation of a fingertip home sleep apnea testing system using deep learning AI and a temporal event localization analysis},
  journal = {SLEEP},
  year = {2025},
  volume = {48},
  number = {5},
  doi = {10.1093/sleep/zsae317}
}
Kostenlos starten →