Ikelos-RWA. Validation of an Automatic Tool to Quantify REM Sleep Without Atonia
Bibliographic record
Abstract
Study Objectives. To present and evaluate an automatic scoring algorithm for quantification of REM-sleep without atonia (RWA) in patients with REM-sleep behaviour disorder (RBD) based on a generally accepted, well-validated visual scoring method, (“Montreal” phasic and tonic) and a recently developed, concise scoring method (Ikelos-RWA). Methods. Video-polysomnographies of 20 RBD patients (68.2 ± 7.2 years) and 20 control patients with periodic limb movement disorder (65.9 ± 6.7 years) were retrospectively analysed. RWA was estimated from chin electromyogram during REM-sleep. Visual and automated RWA scorings were correlated, and agreement ( a) and Cohen's Kappa ( k) calculated for 1735 minutes of REM-sleep of the RBD patients. Discrimination performance was evaluated with receiver operating characteristic (ROC) analysis. The algorithm was then applied on the polysomnographies of a cohort of 232 RBD patients (total analysed REM-sleep: 17,219 minutes) and evaluated, while correlating the different output parameters. Results. Visual and computer-derived RWA scorings correlated significantly (tonic Montreal: r TM = 0.77; phasic Montreal: r PM = 0.78; Ikelos-RWA: r I = 0.97; all p < 0.001) and showed good to excellent Kappa coefficients ( k TM = 0.71; k PM = 0.79; k I = 0.77). The ROC analysis showed high sensitivities (95%-100%) and specificities (84%-95%) at the optimal operation points, with area under the curve (AUC) of 0.98, indicating high discriminating capacity. The automatic RWA scorings of 232 patients correlated significantly ( r TM{I} = 0.95; r PM{I} = 0.91, p < 0.0001). Conclusions. The presented algorithm is an easy-to-use and valid tool for automatic RWA scoring in patients with RBD and may prove effective for general use being publicly available.
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 | 0.001 |
| 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".