Accuracy of Machine Learning Algorithms Based on Electroencephalogram in Sleep Apnea Detection: Systematic Review and Meta-Analysis.
Electroencephalogram-based machine learning models detect sleep apnea with excellent diagnostic accuracy
Accuracy of Machine Learning Algorithms Based on Electroencephalogram in Sleep Apnea Detection: Systematic Review and Meta-Analysis.
Sleep apnea (sleep apnea) is a serious sleep disorder, and its diagnostic gold standard, polysomnography, is costly and time-consuming.
This systematic review evaluated the accuracy of machine learning in detecting sleep apnea from electroencephalogram data and provided an evidence base for further clinical application and future research.
Following the PRISMA-DTA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses of Diagnostic Test Accuracy) and PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020 expanded checklists, we systematically searched PubMed, Embase, Web of Science, Cochrane Library (CENTRAL), Scopus, IEEE Xplore, and ClinicalTrials.gov databases from inception to April 2026.
Meta-regression identified electroencephalogram channel configuration, region, and validation strategy as significant sources of heterogeneity (P=.004, P=.003, and P=.046, respectively).
Multichannel electroencephalogram, deep learning approaches, and hold-out validation strategies generally demonstrated better diagnostic performance.
Only 2 studies evaluated patient-level diagnostic performance, which was summarized qualitatively.
To our knowledge, this is the first systematic review and meta-analysis specifically focused on the diagnostic accuracy of electroencephalogram-based machine learning models in the detection of sleep apnea.
This meta-analysis indicates that machine learning models based on electroencephalogram demonstrate good diagnostic accuracy in detecting sleep apnea at the segment level and show promise as tools for sleep apnea screening and clinical decision support.
However, most current studies are retrospective segment-level analyses, which may overestimate the practical value of this technology in real-world clinical settings.