Multichannel machine learning for polysomnographic diagnosis of obstructive sleep apnea: a Bayesian meta-analysis
Authors:
- Shahana RaniSRShahana Rani
- Esther Yanxin GaoEGEsther Yanxin Gao
- Joel Zuo Er OngJOJoel Zuo Er Ong
- 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
- 16 November 2025
- journal article
- review article
- Published by Springer Nature in European Archives of Oto-Rhino-Laryngology
- Vol. 283 (4) , 2107-2116
Abstract
Background Obstructive sleep apnea (OSA) affects 1 billion people globally, yet over 80% remain undiagnosed. The gold standard for diagnosis, overnight polysomnography, is highly accurate but labor-intensive, leading to delays and increased healthcare burden. Artificial intelligence (AI) models offer a promising alternative. This study pools existing evidence to evaluate AI-based OSA diagnostics. Methods A systematic search of PubMed, Embase, Scopus, Web of Science, and IEEE Xplore identified studies comparing AI models against the apnea-hypopnea index (AHI) for OSA diagnosis. Studies evaluating models using random-split test sets or k-fold cross-validation were included in a Bayesian bivariate meta-analysis and meta-regression. Risk of bias and evidence quality were assessed using QUADAS-2 and GRADE. Results From 6,254 records, 7 studies with 19 AI models trained and tested on 7,547 and 7,471 participants were included. No study had a high risk of bias. AI achieved a pooled sensitivity of 89.2% (95% CrI: 81.5–94.3%) and specificity of 87.1% (95% CrI: 82.6–90.8%). Neural networks (NNs) were the best-performing AI model compared to the other subtypes, achieving a sensitivity of 92.8% (95% CrI: 84.8–96.6%) and specificity of 87.8% (95% CrI: 81.1–92.6%). Age and sex had no effect. No publication bias was detected, and the evidence was of high quality. Conclusion Neural Networks AI models trained on polysomnography demonstrated excellent diagnostic accuracy in diagnosing OSA as compared to traditional machine learning. There is a need for further exploration and external validation of AI models to support their integration into routine sleep medicine practice, hence improving access to efficient and accurate OSA diagnosis. PROSPERO registration: CRD42024534235.Keywords
This publication has 50 references indexed in Scilit:
- 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
- Automatic diagnosis of sleep apnea from biomedical signals using artificial intelligence techniques: Methods, challenges, and future worksWIREs Data Mining and Knowledge Discovery, 2022
- Association of obstructive sleep apnea with thyroid cancer incidence: a systematic review and meta-analysisEuropean Archives of Oto-Rhino-Laryngology, 2022
- A model for obstructive sleep apnea detection using a multi-layer feed-forward neural network based on electrocardiogram, pulse oxygen saturation, and body mass indexSleep and Breathing, 2021
- 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
- Comparison of Different Classifier Algorithms on the Automated Detection of Obstructive Sleep Apnea SyndromeJournal of Medical Systems, 2008
- Meta-analysis of Observational Studies in EpidemiologyA Proposal for ReportingJAMA, 2000