A novel expert classifier approach to pre-screening obstructive sleep apnea during wakefulness
Bibliographic record
Abstract
Obstructive sleep apnea (OSA) is a widespread disorder that is cumbersome to diagnose using the goldstandard, overnight polysomnography (PSG). This paper highlights further development of our Awake-OSA method for predicting whether someone has severe sleep apnea using breath sounds recorded during wakefulness. We propose the use of an expert classification approach that consists of individual majority-voting classifiers. Each classifier is trained to distinguish one class of subject from all other classes. The outcomes of these classifiers are, in turn, combined using a truth matrix to determine the final outcome. Using the breath sound features of 249 subjects, the classifiers attempted to classify 180 subjects as either non-OSA (AHI less than 5) or severe-OSA (AHI greater than 30). 79% and 75% of OSA and non-OSA subjects, respectively, could be classified. Of those classified, the resultant testing sensitivity and specificity were found to be 78% and 86%, respectively. The consistency of the testing to training accuracies indicates the robustness and generalizability of using multiple expert classifiers on the dataset. This technique has the potential to be used in a doctor's office to rapidly and cheaply pre-screen for OSA, so that physicians may be better able to determine which patients are in need of overnight PSG.
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 | 0.007 |
| 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 | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".