A Novel Decision Making Procedure during Wakefulness for Screening Obstructive Sleep Apnea using Anthropometric Information and Tracheal Breathing Sounds
Bibliographic record
Abstract
Obstructive sleep apnea (OSA) is an underdiagnosed common disorder. Undiagnosed OSA, in particular, increases the perioperative morbidity and mortality risks for OSA patients undergoing surgery requiring full anesthesia. OSA screening using the gold standard, Polysomnography (PSG), is expensive and time-consuming. This study offers an objective and accurate tool for screening OSA during wakefulness by a few minutes of breathing sounds recording. Our proposed algorithm (AWakeOSA) extracts an optimized set (3-4) of breathing sound features specific to each anthropometric feature (i.e. age, sex, etc.) for each subject. These personalized group (e.g. age) classification features are then used to determine OSA severity in the test subject for that anthropomorphic parameter. Each of the anthropomorphic parameter classifications is weighted and summed to produce a final OSA severity classification. The tracheal breathing sounds of 199 individuals (109 with apnea/hypopnea index (AHI) < 15 as non-OSA and 90 with AHI ≥ 15 as moderate/severe-OSA) were recorded during wakefulness in the supine position. The sound features sensitive to OSA were extracted from a training set (n = 100). The rest were used as a blind test dataset. Using Random-Forest classification, the training dataset was shuffled 1200-6000 times to avoid any training bias. This routine resulted in 81.4%, 80.9%, and 82.1% classification accuracy, sensitivity, and specificity, respectively, on the blind-test dataset which was similar to the results for the out-of-bag-validation applied to the training dataset. These results provide a proof of concept for AWakeOSA algorithm as an accurate, reliable and quick OSA screening tool that can be done in less than 10 minutes during wakefulness.
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 | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".