Related Experiment Video
Updated: Feb 13, 2026

Drug-Induced Sleep Endoscopy DISE with Target Controlled Infusion TCI and Bispectral Analysis in Obstructive Sleep Apnea
Published on: December 6, 2016
Awake speech recordings for machine learning diagnosis of obstructive sleep apnea: a Bayesian meta-analysis
Esther Yanxin Gao1,2,3, Yunrui Hao1, Nicole Kye Wen Tan1
1Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore.
Artificial Intelligence (AI) speech analysis shows promising accuracy for screening obstructive sleep apnea (OSA). This AI tool, using awake speech, offers a practical, scalable method for diagnosing OSA, a common but often overlooked condition.
Area of Science:
- Medical Technology
- Artificial Intelligence
- Sleep Medicine
Background:
- Obstructive sleep apnea (OSA) is a widespread condition with significant health implications, frequently underdiagnosed.
- Polysomnography (PSG), the standard diagnostic tool, has limited accessibility.
- AI-based speech analysis emerges as a potential non-invasive alternative for OSA screening.
Purpose of the Study:
- To evaluate the diagnostic accuracy of AI models analyzing awake speech for obstructive sleep apnea.
- To identify factors influencing the performance of AI speech analysis in OSA detection.
Main Methods:
- A systematic literature search was conducted across major scientific databases.
- Bayesian bivariate meta-analysis and meta-regression were employed to synthesize data from eligible studies.
- Risk of bias and evidence quality were assessed using QUADAS-2 and GRADE frameworks.
Main Results:
- Eight studies involving 24 AI models were included, analyzing data from 1,060 participants.
- AI models analyzing awake speech achieved a pooled sensitivity of 82.9% and specificity of 83.3%.
- Higher mean participant age correlated with improved sensitivity; other factors like OSA severity did not significantly impact performance.
Conclusions:
- AI models trained on awake speech recordings demonstrate robust diagnostic accuracy for OSA.
- These AI tools present a viable, scalable, and practical screening solution for obstructive sleep apnea in various settings.
More Related Videos
Related Concept Videos
Sleep Apnea
The condition is more prevalent among...
Insufficient Sleep and Sleep Deprivation
Sleep deprivation is a more severe form of sleep loss...
Machines
A free-body diagram of the...
Directing Effect of Substituents: meta-Directing Groups
Stages of Sleep
Before sleep begins, in wakefulness, the brain exhibits primarily beta waves, which are high in frequency and low in amplitude, indicating alertness...
Understanding Sleep
The circadian rhythm, a nearly 24-hour cycle, is deeply influenced by environmental light cues. Light exposure directly affects the hypothalamus, which in turn regulates...

