Investigating low-pressure AI-enabled PAP therapy without compromising AHI: a win for all OSA patients
Bibliographic record
Abstract
Introduction: Despite the advantage of increased comfort, low-pressure Positive Airway Pressure (PAP) therapy raises the Apnea-Hypopnea Index (AHI). We hypothesize our AI-driven cMAP™ algorithm (Hanafi. et al. ERJ 2023 62: PA573), enables PAP therapy at significantly reduced pressures while preserving efficacy. Methods: An ongoing randomized crossover study on PAP-adherent OSA patients (n=50) aims to evaluate cMAP™'s effectiveness in treating OSA with lower mean therapy pressures than conventional auto PAP (APAP). Patients undergo one week of cMAP™ (test) and one week of APAP therapy (control). Pressure and AHI are monitored via the PAP device, and the SleepImage™ Ring tracks sleep staging and SleepImage AHI (sAHI). Results: Preliminary results across subjects (2 female, 4 male, significance determined via paired t-tests) show cMAP™ delivers lower mean nightly therapy pressure than APAP (p<0.01), averaging -1.8±0.6 cmH20 (±S.D.). No differences are observed in AHI (p=0.75) or sAHI (p=0.69). 2/6 subjects spent more time in stable non-REM sleep with cMAP™ (+14% of night, p<0.05) with no differences in the remaining 4 patients. Conclusion: cMAP™ has the potential to improve pressure related comfort and quality of care. Future work includes developing a technique to tailor cMAP™’s AI component to individual subjects. erj;64/suppl_68/PA4470/F1 F1 F1
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 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".