0448 CLINICAL VALIDATION OF A DIAGNOSTIC PATCH FOR THE DETECTION OF SLEEP APNEA
Bibliographic record
Abstract
Portable home sleep monitors are being increasingly utilized in clinical practice for diagnosing sleep apnea. However, most type III home monitors are difficult for patients to set up and wearing the monitors is disruptive to patient’s typical sleep pattern. The diagnostic value of an inexpensive easy-to-use light-weight flexible skin-adhesive patch (SomnaPatch) that minimally affects sleep was evaluated in this study. Simultaneous polysomnography (PSG) and the diagnostic patch recordings were made in 179 subjects (mean age 54.0 ± 13.6 y, 55% male) selected from the databases of patients previously tested with PSG to ensure even representation of the clinically important apnea-hypopnea index (AHI) ranges. The skin-adhesive diagnostic patch weighs less than one ounce and records nasal pressure, blood oxygen saturation, pulse rate, respiratory effort, sleep time and body position (S3C4O2P2E3R2 category). To compare the apnea-hypopnea index of the diagnostic patch with polysomnography, all recordings were auto-scored with the Somnolyzer software (Respironics). Bland-Altman analysis was performed. Sensitivity, specificity and accuracy were calculated and receiver operating characteristic (ROC) curves were constructed for six AHI thresholds (5, 10, 15, 20, 25 and 30 events per hour). The rate of clinical agreement and positive likelihood ratio were calculated. Overnight recordings from 174 subjects were included in the final analysis. All six ROC curves had area under the curve of over 0.9. Sensitivity, specificity and accuracy for the optimal threshold of AHI≥15 were 0.86, 0.83 and 0.85 respectively. Positive likelihood ratio (LR+) was 7.4. Bland-Altman analysis showed that the bias was 0.9 events per hour and the limits of agreement were 18.1 and -16.1. The rate of clinical agreement between recordings with PSG AHI≥30 and patch AHI≥30 and was 85%. The rate of clinical agreement between recordings with PSG AHI<30 and the patch AHI within (PSG AHI ±10) was 89%. The total rate of clinical agreement was 87.4% with 95% confidence interval of 81.4%-91.9%. The new diagnostic patch offers excellent clinical value for detecting sleep apnea across all severity levels as compared with standard in-lab polysomnography. Research was supported by NIH grant R44 HL123196.
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 | 0.001 | 0.012 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| 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".