1119 Validation of a Portable Sleep Electroencephalography Device in Good Sleepers and People with Sleep Apnea
Bibliographic record
Abstract
Abstract Introduction Sleep wearable restricted to accelerometry or heart rate monitoring have proved to be helpful to delineate sleep-wake profiles outside of the laboratory environment, but have limited accuracy and only provide indirect estimations of sleep and wake states. This study aimed to assess the validity of a novel electroencephalography headband for ambulatory sleep monitoring as compared to standard polysomnography in good sleepers and individuals with sleep apnea. Methods Forty-seven adult males and females from the community took part to this study. This includes a preliminary sample of eight individuals with sleep apnea detected through level 1 polysomnography. All participants underwent one night of in-laboratory sleep recording with the portable EEG headband (MUSE-S, Interaxon) and simultaneous standard polysomnography (Embla N7000/RemLogic, Natus). The Muse-S headband is a commercially available consumer headband with 7 EEG sensors: 2 on the forehead, 2 behind the ears, and 3 reference sensors. MUSE-S data was scored using an automated sleep staging algorithm. Polysomnography data was scored by an independent registered technologist who was blinded to the MUSE-S algorithm-based scoring. Results In the overall sample, the accuracy of the Muse-S relative to standard polysomnography ranged between 88% and 96% across all sleep stages, with a sensitivity of 79% to 92%, and a specificity of 90% to 99%. Cohen’s Kappa for all sleep stages combined was 0.76 (CI:0.75-0.76). Analyses per sleep stages showed that Cohen’s Kappa scores were in the fair agreement range for NREM 1 sleep (K=0.41, CI:0.39-0.43), increased to the substantial agreement range for both NREM 2 (K=0.75, CI:0.74-0.75) and NREM3 sleep (K=0.77, CI:0.76-0.77), and further increased to the near perfect agreement range for REM sleep (K=0.85, CI:0.85-0.86) and wake (K=0.84, CI: 0.83-0.84). Similar results were obtained in the subgroup with sleep apnea (overall K= 0.87, CI:0.85-0.88; NREM 1 K=0.33, CI:0.28-0.38; NREM 2 K=0.72, CI:0.70-0.73; NREM3 K=0.81, CI:0.79-0.79; REM K=0.80, CI:0.78-0.82) and wake (K=0.86, CI:0.85-0.88). Conclusion Portable EEG-based sleep monitoring with the MUSE-S shows good validity for sleep macroarchitecture variables relative to standard polysomnography. Fair to near perfect concordance was observed across sleep stages in a diverse sample of good sleepers and people with sleep disorders. Support (if any)
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 | 0.003 | 0.008 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.001 |
| 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".