Accuracy of Artificial Intelligence in Diagnosing Obstructive Sleep Apnea Using Photoplethysmography: Systematic Review and Meta-Analysis
Genauigkeit von künstlicher Intelligenz zur Diagnose obstruktiver Schlafapnoe mittels Photoplethysmographie: systematische Übersichtsarbeit und Metaanalyse
Journal of Medical Internet Research · 25.09.2026 · 28 · e78718-e78718
DOI: 10.2196/78718 ↗Auf einen Blick
13 Studien mit 9.983 Teilnehmenden zeigen eine moderate diagnostische Genauigkeit von KI-Modellen auf Basis von PPG für OSA. Gepoolt lagen Sensitivität und Spezifität bei 79,6 % bzw. 76,5 %.
Fragestellung
Wie genau diagnostizieren KI-basierte Verfahren mit Photoplethysmographie (PPG) eine obstruktive Schlafapnoe bei Erwachsenen im Vergleich zur konventionellen Schlafdiagnostik?
Methode
Systematische Übersichtsarbeit und Metaanalyse von Beobachtungsstudien; Suche in PubMed, Embase, Scopus, Web of Science und IEEE Xplore bis 3. November 2025; QUADAS-2 und GRADE; Bayesian bivariate Metaanalyse.
Ergebnisse
13 Studien mit 9.983 Teilnehmenden. Sensitivität 79,6 % (95 %-CrI 55,5 %–93,8 %), Spezifität 76,5 % (95 %-CrI 48,2 %–94,0 %). Höhere Spezifität bei Deep Learning (82,9 %) als bei traditionellem Machine Learning (63,6 %).
Einschränkungen
Alle Studien hatten niedriges oder unklare(s) Verzerrungsrisiko; kleine Stichproben; Unterrepräsentation bestimmter Regionen; mögliche Confounder.
Schlussfolgerung der Autor:innen
KI-Modelle auf Basis von PPG haben eine angemessene Genauigkeit und könnten als kostengünstiges Screening-Instrument dienen. Weitere Forschung, besonders zu Deep Learning, ist erforderlich.
Kernaussagen
- Sensitivität 79,6 % und Spezifität 76,5 %
- Deep Learning zeigte höhere Spezifität als traditionelles Machine Learning
- Evidenzqualität insgesamt moderat
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Systematische Übersicht in der Zeitschrift Journal of Medical Internet Research, online erschienen am 25.09.2026. Verfasst von Brian Sheng Yep Yeo und 12 weiteren Autor:innen. Beteiligte Einrichtung: Yong Loo Lin School of Medicine, National University of Singapore, 10 Medical Dr, Singapore, 117597, Singapore, 65 65161048. Hauptthemen laut MEDLINE: Artificial Intelligence, Photoplethysmography, Sleep Apnea, Obstructive. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Background
The traditional method for diagnosing obstructive sleep apnea (OSA) through polysomnography may be expensive and inaccessible. Recent developments in AI propose the use of photoplethysmography (PPG) to aid OSA diagnosis.
Objective
This study seeks to evaluate the diagnostic accuracy of an AI-based approach in diagnosing OSA using PPG.
Methods
PubMed, Embase, Scopus, Web of Science, and IEEE Xplore were searched from inception to November 3, 2025. The inclusion criteria comprised observational studies that evaluated the accuracy of AI-based methods of OSA diagnosis using PPG compared with conventional sleep testing used in adults. We excluded case reports, case series, reviews, meta-analyses, letters, conference abstracts, pediatric studies, animal studies, foreign language studies, studies with incomplete data, and studies focusing on individual apneic events without patient-level classification. The outcome of interest was the diagnostic accuracy of PPG-based AI models for OSA, as assessed in primary studies using random split tests, cross-validation, or external validation. Independent reviewers extracted data and assessed risk of bias using the QUADAS-2 (Quality Assessment of Diagnostic Accuracy Studies-2) tool. A Bayesian bivariate meta-analysis was used to pool estimates. Further subgroup, sensitivity, and meta-regression analyses were conducted. Overall quality of evidence was assessed using the GRADE (Grading of Recommendations, Assessment, Development and Evaluations) framework.
Results
From 12,579 records, we included 13 studies, comprising 9983 participants. All studies were rated as either low or unclear for risk of bias. The overall evidence quality was moderate. AI trained on PPG achieved a pooled sensitivity of 79.6% (95% credible interval [CrI] 55.5%‐93.8%) and specificity of 76.5% (95% CrI 48.2%‐94.0%), compared to conventional diagnosis. The overall specificity increased (apnea-hypopnea index [AHI] ≥5: 63.6%; AHI ≥15: 81.8%; AHI ≥30: 85.1%), but overall sensitivity decreased (AHI ≥5: 87.2%; AHI ≥15: 79.7%; AHI ≥30: 76.7%) with greater categorical AHI severity cutoffs. Additionally, deep learning models achieved a higher specificity (82.9%) than traditional machine learning (63.6%). OSA prevalence and device type were not clearly associated with sensitivity or specificity.
Conclusions
AI models trained on PPG have reasonable accuracy and may potentially serve as a low-cost screening tool. However, limitations such as small sample sizes, potential sources of bias, underrepresentation of certain geographic regions, and the influence of potential confounding factors highlight the necessity for further research. Future work should focus on deep learning to improve the feasibility and accessibility of this approach in primary care.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Yong Loo Lin School of Medicine, National University of Singapore, 10 Medical Dr, Singapore, 117597, Singapore, 65 65161048.
- Department of Otorhinolaryngology - Head and Neck Surgery, Singapore General Hospital, Outram Road, Singapore, 169608, Singapore, +6563214790.
- Duke-NUS Sleep Centre, SingHealth, Singapore, Singapore.
- Department of Respiratory and Critical Care Medicine, Singapore General Hospital, Singapore, Singapore.
- School of Automation, Southeast University, Nanjing, China.
Zitieren
APA
Yeo, B. S. Y., Gao, E. Y., Tan, J. E. X., Koo, J. Y., Lee, Y. S., Tan, N. K. W., Ng, A. C. W., Leong, Z. H., Ong, T. H., Leow, L. C., Huang, G. B., Tan, B. K. J., & Toh, S. T. (2026). Accuracy of Artificial Intelligence in Diagnosing Obstructive Sleep Apnea Using Photoplethysmography: Systematic Review and Meta-Analysis. Journal of Medical Internet Research, 28, e78718-e78718. https://doi.org/10.2196/78718
Vancouver
Yeo BSY, Gao EY, Tan JEX, Koo JY, Lee YS, Tan NKW, et al. Accuracy of Artificial Intelligence in Diagnosing Obstructive Sleep Apnea Using Photoplethysmography: Systematic Review and Meta-Analysis. Journal of Medical Internet Research. 2026;28:e78718-e78718. doi:10.2196/78718
BibTeX
@article{Yeo2026,
author = {Yeo, Brian Sheng Yep and Gao, Esther Yanxin and Tan, Joan Ern Xin and Koo, Jun Yuan and Lee, Yi Siang and Tan, Nicole Kye Wen and Ng, Adele Chin Wei and Leong, Zhou Hao and Ong, Thun How and Leow, Leong Chai and Huang, Guang-Bin and Tan, Benjamin Kye Jyn and Toh, Song Tar},
title = {Accuracy of Artificial Intelligence in Diagnosing Obstructive Sleep Apnea Using Photoplethysmography: Systematic Review and Meta-Analysis},
journal = {Journal of Medical Internet Research},
year = {2026},
volume = {28},
pages = {e78718--e78718},
doi = {10.2196/78718}
}
EUVIMED