Automated analysis of digital oximetry in the diagnosis of obstructive sleep apnoea
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
BACKGROUND: The gold standard diagnostic test for obstructive sleep apnoea (OSA) is overnight polysomnography (PSG) which is costly in terms of time and money. Consequently, a number of alternatives to PSG have been proposed. Oximetry is appealing because of its widespread availability and ease of application. The diagnostic performance of an automated analysis algorithm based on falls and recovery of digitally recorded oxygen saturation was compared with PSG. METHODS: Two hundred and forty six patients with suspected OSA were randomly selected for PSG and automated off line analysis of the digitally recorded oximeter signal. RESULTS: The PSG derived apnoea hypopnea index (AHI) and oximeter derived respiratory disturbance index (RDI) were highly correlated (R = 0.97). The mean (2SD) of the differences between AHI and RDI was 2.18 (12.34)/h. The sensitivity and specificity of the algorithm depended on the AHI and RDI criteria selected for OSA case designation. Using case designation criteria of 15/h for AHI and RDI, the sensitivity and specificity were 98% and 88%, respectively. If the PSG derived AHI included EEG based arousals as part of the hypopnea definition, the mean (2SD) of the differences between RDI and AHI was -0.12 (15. 62)/h and the sensitivity and specificity profile did not change significantly. CONCLUSIONS: In a population of patients suspected of having OSA, off line automated analysis of the oximetry signal provides a close estimate of AHI as well as excellent diagnostic sensitivity and specificity 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.
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) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.004 |
| 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) | 0.001 | 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 it