Preliminary Estimates of the Diagnostic Accuracy of Video Clips for Obstructive Sleep Apnea in Children
Bibliographic record
Abstract
BACKGROUND: Diagnosing obstructive sleep apnea (OSA) in children is challenging, with long wait times for polysomnography (PSG). This study assessed the diagnostic accuracy of home-recorded video clips for OSA compared to PSG. METHODS: Children (2-18 years) referred for PSG for suspected OSA were enrolled. Parents recorded video clips of their child sleeping and completed the Pediatric Sleep Questionnaire (PSQ). Blinded clinicians scored videos using the Monash Obstructive Sleep Apnea score (MS). Participants underwent PSG, and outcomes included obstructive apnea-hypopnea index (OAHI) and oximetry metrics (i.e., McGill Oximetry Score [MOS]; 3% Oxygen Desaturation Index [ODI3]). Diagnostic characteristics of MS, PSQ, MOS, and ODI3 were compared for detection of any (OAHI ≥ 1.5 events/h) and moderate-severe OSA (OAHI ≥ 5 events/h). RESULTS: Forty-one children (age 7.0 years, 49% female) participated. Median OAHI was 0.6 events/h (IQR 0.3, 3.1); 16 (39%) had OAHI ≥ 1.5 events/h, 5 (12%) had OAHI ≥ 5 events/h. PSQ identified 36 (88%) participants with a score ≥ 0.33. One child had MOS ≥ 2; ODI3 was ≥ 4.3 in 8 (20%) and > 7 in 6 (15%). Mean MS was 3.6 (SD 2.1). MS had 81.2% sensitivity and 52.0% specificity for any OSA and 100% sensitivity and 44.4% specificity for moderate-severe OSA. A combination of MS and ODI3 improved diagnostic accuracy with an AUC of 98.3. CONCLUSION: MS demonstrated high sensitivity but low specificity for the detection of moderate-severe OSA. Video scores outperformed PSQ but were less accurate than oximetry. Combining MS and ODI3 yielded the strongest diagnostic characteristics. Video scores may aid in pediatric OSA screening.
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.
How this classification was reachedexpand
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 | 0.000 | 0.014 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".