Validation of <i>RBDtector</i> : An Open‐Source Automated Software for Scoring <scp>REM</scp> Sleep Without Atonia
Bibliographic record
Abstract
ABSTRACT Accurate quantification of REM sleep without atonia (RSWA) is essential in the diagnosis of idiopathic/isolated REM sleep behaviour disorder (iRBD). This study aims to validate RBDtector , a free and open‐source tool for automated RSWA quantification using the Sleep Innsbruck Barcelona (SINBAR) scoring method, by comparing its performance against human visual scoring in a large independent cohort of subjects with iRBD and healthy controls. Muscle activity from 118 iRBD participants and 37 healthy controls that underwent polysomnography was analysed by RBDtector and compared with human visual scoring. Diagnostic performance was evaluated using receiver operating characteristic curves, and optimal cut‐offs for iRBD screening and diagnosis were determined. The results of RSWA quantification were applied to survival analyses of time to phenoconversion. RBDtector showed excellent agreement with human visual scoring, particularly in ‘any’ RSWA activity (Pearson's correlation = 0.89, R 2 = 0.79, p < 0.001). RBDtector identified iRBD subjects with 95.6% sensitivity and 95.5% specificity by using a cutoff of 33.0% for combined ‘any’ RSWA activity in the submentalis and flexor digitorum superficialis muscles, with each muscle in isolation providing comparable results. In iRBD patients, each 10% increase in submentalis ‘any’ activity was associated with a 23% increase in the risk of phenoconversion (HR = 1.23, 95% CI [1.06, 1.44], p = 0.008), while no associations were observed with increased activity in the flexor digitorum superficialis or tibialis anterior. RBDtector provides accurate, automated RSWA quantification comparable to human visual scoring, offering a reliable and efficient method to support the diagnosis of iRBD and identify iRBD at a higher risk of phenoconversion.
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 | 0.006 | 0.021 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.003 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.003 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| 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".