Detecting obstructive sleep apnea in children by self-affine visualization of oximetry
Bibliographic record
Abstract
Obstructive sleep apnea (OSA), characterized by cessations of breathing during sleep due to upper airway collapse, can affect the healthy growth and development of children. The gold standard for OSA diagnosis, polysomnography(PSG), is expensive and resource intensive, resulting in long waiting lists to perform a PSG. Previously, we investigated the time-frequency analysis of blood oxygen saturation (SpO2) to screen for OSA. We used overnight pulse oximetry from 146 children, collected using a smartphone-based pulse oximeter (Phone Oximeter), simultaneously with standard PSG. Sleep technicians manually scored PSG and provided the average of apnea/hypoapnea events per hour (AHI). In this study, we proposed an alternative method for analyzing SpO2, in which a set of contracting transformations form a self-affine set with a 2D attractor, previously developed for qualitative visualization of the photoplethysmogram and electroencephalogram. We applied this technique to the overnight SpO2signal from individual patients and extracted features based on the distribution of points (radius and angle) in the visualization. The cloud of points in children without OSA (NonOSA) was more confined than in children with OSA, which was reflected by more empty pixels (radius and angles). The maximum value, skewness and standard deviation of the distribution of points located at different radius and angles were significantly (Bonferroni corrected) higher in NonOSA compared to OSA children. To detect OSA defined at different levels (AHI≥5, AHI≥10 and AHI≥15), three multivariate logistic regression models were implemented using a stepwise feature selection and internally validated through bootstrapping. The models (AHI≥5, AHI≥10, AHI≥15), consisting of 3, 4 and 1 features respectively, provided a bootstrap-corrected AUC of 73%, 81%, 73%. Thus, applying this visualization to nocturnal SpO2could yield both visual and quantitative information that might be useful for screening children for 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 | 0.000 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| 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".