Measures of overnight oxygen saturation to characterize sleep apnea severity and predict postoperative respiratory depression
Bibliographic record
Abstract
Abstract Background Sleep apnea syndrome, characterized by recurrent cessation (apnea) or reduction (hypopnea) of breathing during sleep, is a major risk factor for postoperative respiratory depression. Challenges in sleep apnea assessment have led to the proposal of alternative metrics derived from oxyhemoglobin saturation (SpO2), such as oxygen desaturation index (ODI) and percentage of cumulative sleep time spent with SpO2 below 90% (CT90), as predictors of postoperative respiratory depression. However, their performance has been limited with area under the curve of 0.60 for ODI and 0.59 for CT90. Our objective was to propose novel features from preoperative overnight SpO2 which are correlated with sleep apnea severity and predictive of postoperative respiratory depression. Methods Preoperative SpO2 signals from 235 surgical patients were retrospectively analyzed to derive seven features to characterize the sleep apnea severity. The features included entropy and standard deviation of SpO2 signal; below average burden characterizing the area under the average SpO2; average, standard deviation, and entropy of desaturation burdens; and overall nocturnal desaturation burden. The association between the extracted features and sleep apnea severity was assessed using Pearson correlation analysis. Logistic regression was employed to evaluate the predictive performance of the features in identifying postoperative respiratory depression. Results Our findings indicated a similar performance of the proposed features to the conventional apnea–hypopnea index (AHI) for assessing sleep apnea severity, with average area under the curve ranging from 0.77 to 0.81. Notably, entropy and standard deviation of overnight SpO2 signal and below average burden showed comparable predictive capability to AHI but with minimal computational requirements and individuals’ burden, making them promising for screening purposes. Our sex-based analysis revealed that compared to entropy and standard deviation, below average burden exhibited higher sensitivity in detecting respiratory depression in women than men. Conclusion This study underscores the potential of preoperative SpO2 features as alternative metrics to AHI in predicting postoperative respiratory.
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 | 0.000 |
| 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 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".