Comparison of AI-driven scoring with manual scoring of lab-based polysomnography data
Bibliographic record
Abstract
Introduction: Polysomnography (PSG) with manual sleep scoring is the gold standard in diagnosing sleep pathologies. Since manual scoring is time consuming and prone to inter-/intra-patient variability, alternative AI-driven automatic procedures were developed. Aim and objectives: The aim of this study was to compare AI-driven sleep scoring using two different approaches with manual scoring. Methods: 24 consecutive PSGs were scored manually and compared with two different AI-driven scoring systems - Michele Sleep Scoring software (MSS, Cerebra Medical Ltd. in Winnipeg, MB, Canada) and ASEEGA® software (Physip© SA in Paris) / Embla® RemlogicTM software. The scoring criteria of AASM guidelines 2014 were applied. Results: PSGs of 24 patients (15 men) with a mean age of 55 ±14years, a BMI of 32.7 ±7.2 kg/m2 and mean Epworth Sleepiness Scale 8.4 ±4 were assessed. Overall, there was a good consistency between AI-driven and manually scored records. However, compared to the reference, MSS overestimated sleep stages 1&2 and unterestimated sleep stage 3, while all NREM sleep stages were scored more accurately with ASEEGA/Remlogic. REM sleep using MSS was in good agreement with manual scoring, while ASSEGA/Remlogic tended to overestimate REM Sleep. AHI was underestimated in both AI-driven methods, while ODI was scored more accurately in MSS, compared to manual scoring. Conclusion: In our study comparing AI-driven sleep scoring with manual scoring, sleep stages were scored more accurately using ASEEGA/Remlogic, while AHI was underestimated in both AI-driven scoring methods. In summary, taking into account certain limits AI-driven scoring of PSGs is a useful tool in diagnosing sleep disturbances.
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 | 0.008 | 0.026 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".