0597 Precision of Sleep-Disordered Breathing Event Classification Using Simulated Home Sleep Apnea Testing in Patients with Spinal Cord Injury, or Disease
Bibliographic record
Abstract
Abstract Introduction Sleep-disordered breathing (SDB) is highly prevalent among patients with spinal cord injury or disease (SCI/D). In-laboratory polysomnography (PSG) is difficult for these patients due to functional limitations and the physical construction of most sleep laboratories. Our objective was to evaluate the concordance between simulated HSAT and PSG in identifying SDB severity and subtypes of respiratory events in this patient population. Methods Within a larger study, 33 Veterans with SCI/D completed one night of in-laboratory PSG. Limited-channel HSAT was simulated by extracting 5 channels from PSG signals to include nasal pressure, thermistor, thoracic and abdominal belts, and oxygen saturation. Results Mean age of patients was 59.8 ± 10.9 years; 87.9% were male, and the average BMI was 28.1 ± 6.3. The mean Apnea-Hypopnea Index (AHI) from PSG was 35.5 ± 22.7. The mean Respiratory Event Index (REI) based on simulated HSAT was 22.5 ± 18.6. Thirty-one patients (93.9%) had SDB defined as AHI ≥5/hour. Simulated limited-channel HSAT accurately identified 32 out of 33 patients (96.96%). When SDB was further classified into mild (AHI 5-15 events/hr), moderate (AHI 15-30 events/hr), and severe (AHI>30/hr), simulated HSAT consistently underestimated the severity of underlying SDB. Spearman correlation between estimating AHI (PSG-HSAT) and subtypes of respiratory events was primarily accounted for by the difference in the number of hypopneas (r=0.72, -0.021 and -0.001 for hypopneas, obstructive and central apneas, respectively). Conclusion Our findings support the diagnostic utility of HSAT in SCI/D patients with SDB; however, HSAT underestimation of SDB may lead to difficulties in optimizing therapy. The misclassification of SDB severity is mainly driven by the number of hypopneas. Classification of hypopneas as obstrcutive or central may shed further light on the nature of this difference. Further research on the usability of HSAT devices in this patient population is needed. Support VA Rehabilitation Research and Development Service (RX002116; PI Badr and RX002885; PI Sankari) and NIH/NHLBI (K24HL143055; PI: Martin)
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 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 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.002 |
| 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) | 0.000 | 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 teacher head, 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".