Awake speech recordings for machine learning diagnosis of obstructive sleep apnea: a Bayesian meta-analysis
Authors:
- Esther Yanxin GaoEGEsther Yanxin Gao
- Yunrui HaoYHYunrui Hao
- Nicole Kye Wen TanNTNicole Kye Wen Tan
- Adele Chin Wei NgANAdele Chin Wei Ng
- Zhou Hao LeongZLZhou Hao Leong
- Chu Qin PhuaCPChu Qin Phua
- Thun How OngTOThun How Ong
- Leong Chai LeowLLLeong Chai Leow
- Guang-Bin HuangGHGuang-Bin Huang
- Benjamin Kye Jyn TanBTBenjamin Kye Jyn Tan
- Song Tar TohSTSong Tar Toh
Open Access
- 8 December 2025
- journal article
- research article
- Published by Springer Nature in Journal of Clinical Sleep Medicine
- Vol. 22 (1) , 5
Abstract
Study objectives Obstructive sleep apnea (OSA) is a prevalent but underdiagnosed condition linked to serious health risks. Due to the limited accessibility of polysomnography (PSG), AI (Artificial Intelligence)-based speech analysis has gained attention as a non-invasive screening tool. This Bayesian meta-analysis evaluates the diagnostic accuracy of AI models trained on awake speech and examines factors affecting performance. Methods We systematically searched Medline/PubMed, Embase, Scopus, Web of Science, and IEEE Xplore databases. Eligible studies included adults with OSA diagnosis via in-lab polysomnography or home sleep apnea tests and evaluated AI models using speech recordings. Models evaluated using random-split test sets or k-fold cross-validation were included in a Bayesian bivariate meta-analysis and meta-regression. Publication bias was examined using a selection model approach, while risk of bias and evidence quality were assessed with QUADAS-2 and GRADE. Results From 6,254 screened articles, 8 studies comprising 24 AI models, trained and tested on 1,060 and 825 participants were included. All studies used professional microphone recordings in the controlled hospital settings. AI models analysing awake speech recordings demonstrated pooled sensitivity and specificity of 82.9% (95% CrI: 80.0–86.4%) and 83.3% (95% CrI: 80.7–86.1%), respectively. The diagnostic odds ratio was 24.3 (95% CrI: 18.2–35.0). Higher mean age improved sensitivity. No significant effects were seen for OSA severity, model type, OSA prevalence, or male percentage. Publication bias was not evident. Conclusion AI models trained on awake speech recordings demonstrate good diagnostic accuracy for OSA and hold potential as a practical, scalable screening tool in both clinical and community-based settings.Keywords
This publication has 42 references indexed in Scilit:
- Multichannel machine learning for polysomnographic diagnosis of obstructive sleep apnea: a Bayesian meta-analysisEuropean Archives of Oto-Rhino-Laryngology, 2025
- Electrocardiogram heart rate variability for machine learning diagnosis of obstructive sleep apnoea: A Bayesian meta-analysisSleep and Breathing, 2025
- Artificial intelligence facial recognition of obstructive sleep apnea: a Bayesian meta-analysisSleep and Breathing, 2024
- DTAmetasa: An R shiny application for meta‐analysis of diagnostic test accuracy and sensitivity analysis of publication biasResearch Synthesis Methods, 2023
- A likelihood‐based sensitivity analysis for publication bias on the summary receiver operating characteristic in meta‐analysis of diagnostic test accuracyStatistics in Medicine, 2022
- Association of obstructive sleep apnea with thyroid cancer incidence: a systematic review and meta-analysisEuropean Archives of Oto-Rhino-Laryngology, 2022
- Severity evaluation of obstructive sleep apnea based on speech featuresSleep and Breathing, 2020
- Graphical enhancements to summary receiver operating characteristic plots to facilitate the analysis and reporting of meta‐analysis of diagnostic test accuracy dataResearch Synthesis Methods, 2020
- Diagnosis and Management of Obstructive Sleep ApneaJAMA, 2020
- Meta-analysis of Observational Studies in EpidemiologyA Proposal for ReportingJAMA, 2000