Home Polygraphy in Children With Autism Spectrum Disorder: A Feasibility Study
Bibliographic record
Abstract
Abstract Introduction: Children with autism spectrum disorder (ASD) have higher prevalence of obstructive sleep apnea (OSA) than typically developing children. Diagnosis of OSA traditionally requires polysomnography (PSG), which can be challenging for children with ASD, and limited by long wait times. Home-based polygraphy is an alternative diagnostic test but is not widely available, emphasizing the need for alternative screening tools. Parent-recorded video clips, reviewed by clinicians, are a potential non-invasive screening tool, but their validity remains under-evaluated. This pilot study aims to assess feasibility and diagnostic characteristics of video clips compared to polygraphy in children with ASD. Methods: Children aged 4-18 years with ASD referred for suspected OSA were recruited. Parents recorded 3 smartphone video clips, which were scored by a pediatric sleep physician using the Monash video score (1-8; score ≥3 indicates OSA). Participants also completed the Pediatric Sleep Questionnaire (PSQ, positive if score > 0.33) and underwent home polygraphy, scored by the obstructive apnea hypopnea index (oAHI, events/hour), oxygen desaturation index 3% (ODI3, using thresholds ≥ 4.3 and > 7 events/hour) and McGill Oximetry Score (MOS, positive if ≥ 2). Sensitivity, specificity and receiver-operator curves were analyzed to compare diagnostic performance across tools for moderate-severe OSA (OAHI ≥ 5 events/hour). Results: Twenty-three children participated in this study. Fifteen (65%) of the children (median age 7.1, 100% male) provided video clips, all of good quality. The median oAHI was 2.4 events/hour (IQR 1.2, 4.0), and 27% had moderate-severe OSA. The PSQ identified 14 (93.3%) children with a score > 0.33. Three children had MOS ≥ 2, ODI3 was ≥ 4.3 in 7 (46.7%) and > 7 in 6 (40%) children. The median Monash score was 3.0 (IQR 1.5, 5.5). The Monash score had 100% sensitivity and 50% specificity for detecting moderate-severe OSA. Diagnostic characteristics of screening tools are presented in Table 1. The video scoring had a diagnostic accuracy of AUC 78.4 for detecting moderate-severe OSA. AUC increased when video score was combined with oximetry metrics. Conclusion: Monash score showed high sensitivity but low specificity in detecting moderate-severe OSA. Video scores outperformed PSQ and MOS but not ODI3 metrics. All video clips were of high quality for interpretation. Video scoring may serve as a viable screening tool to identify OSA in children with ASD, and this study demonstrates its feasibility for larger-scale validation. Table 1: Sensitivity and specificity of different tools with accepted cutoff points for moderate to severe OSA.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 source (direct Gemma or distilled Codex), 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".