Estimating the risk of obstructive sleep apnea during wakefulness using facial images: A review
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Obstructive sleep apnea (OSA) is a chronic sleep-related breathing disorder associated with cardiovascular diseases, cognitive impairments, and an increased risk of accidents. Although polysomnography (PSG) stands as the gold standard for diagnosing OSA, its limitations – such as being cumbersome, expensive, and having long waitlists – have motivated researchers to develop alternative screening methods. Facial photography, serving as an accessible modality, offers insights into anatomical structures linked to OSA. This study aims to comprehensively review existing research on leveraging facial images to estimate OSA severity. We first investigate the physiological intersections between OSA and craniofacial structures. Furthermore, we discuss extracted facial image features, employed feature selection techniques, and details of developed models aimed at detecting OSA severity. Through a comprehensive discussion of current findings and limitations within the field, we aim to shed light on critical gaps necessitating attention in future research directions. • First review investigating the association between facial photography and OSA. • Offering comprehensive list of models and features employed from facial photography. • Exploring gaps and limitations and delivering insights for future directions.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.003 | 0.001 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.002 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it