Pulse oximetry recorded from the Phone Oximeter for detection of obstructive sleep apnea events with and without oxygen desaturation in children
Bibliographic record
Abstract
Obstructive sleep apnea (OSA) disrupts normal ventilation during sleep and can lead to serious health problems in children if left untreated. Polysomnography, the gold standard for OSA diagnosis, is resource intensive and requires a specialized laboratory. Thus, we proposed to use the Phone Oximeter™, a portable device integrating pulse oximetry with a smartphone, to detect OSA events. As a proportion of OSA events occur without oxygen desaturation (defined as SpO2 decreases ≥ 3%), we suggest combining SpO2 and pulse rate variability (PRV) analysis to identify all OSA events and provide a more detailed sleep analysis. We recruited 160 children and recorded pulse oximetry consisting of SpO2 and plethysmography (PPG) using the Phone Oximeter™, alongside standard polysomnography. A sleep technician visually scored all OSA events with and without oxygen desaturation from polysomnography. We divided pulse oximetry signals into 1-min signal segments and extracted several features from SpO2 and PPG analysis in the time and frequency domain. Segments with OSA, especially the ones with oxygen desaturation, presented greater SpO2 variability and modulation reflected in the spectral domain than segments without OSA. Segments with OSA also showed higher heart rate and sympathetic activity through the PRV analysis relative to segments without OSA. PRV analysis was more sensitive than SpO2 analysis for identification of OSA events without oxygen desaturation. Combining SpO2 and PRV analysis enhanced OSA event detection through a multiple logistic regression model. The area under the ROC curve increased from 81% to 87%. Thus, the Phone Oximeter™ might be useful to monitor sleep and identify OSA events with and without oxygen desaturation at home.
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 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| 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".