0667 Learning To Phenotype RLS From Zappelphilipp (Fidgety Philip) Cartoons
Bibliographic record
Abstract
Individuals with neuropsychiatric and/or neurodevelopmental conditions often display disruptive behaviours such as hyperkinesia, hypermotor-restlessness, hyper/hypo-arousability and hypermotor events (H-behaviours). This terminology, introduced by the Video-Working-Group of the International Paediatric Sleep Association (IPSA), allows for a neutral, training background independent, in-depth phenotyping of structured behavioural observations. As a first step, we investigated how to develop a shared, neutral, annotation language for describing and not interpreting H-behaviours, using qualitative open-ended and pictogram-based annotations (O-a; P-a). Using REDCap data collection software, seven research assistants without prior formal training analyzed: (A) three ‘Fidgety Philip’ (FP) cartoons, using qualitative O-a and reviewed possible applications for P-a. (B) Then, 12 Suggested Clinical Immobilization Test (SCIT) video snapshots of five participants were analyzed using O-a and the exercise was repeated 2 days later, in a randomized order; the same 2-day procedure was repeated using P-a. (C) Inter-/Intra-observer variability of (A) & (B) results was investigated. (A) FP-cartoons: O-a were divided into descriptions (n=168, mean=8.0 ± 3.8) and interpretations (n=106, mean=5.0 ± 3.1); with each cartoon, the number of descriptions increased compared to interpretations. (B) SCIT snapshots: Day 1 & 2 data were separated into descriptive vs. interpretive results: O-a (median=6/7 vs. median=1/1) and P-a (median=1/2 vs. median=2/1); then pictogram categorization was reassessed and developed further. (C) Intra-observer reliability for descriptive/interpretative O-a was low (descriptive statistics: 61.9%/36.6%). Inter-observer reliability of P-a for overarching categories was higher (intraclass correlation coefficients: head 0.895; upper limbs: 0.823; lower limbs: 0.878) but low for body tension in dependency of posture (0.588). (A) and (B) With experience, the ability to describe and reduce interpretations increased, P-a enhanced this process. (C) Descriptions yielded low and high inter-observer consistency via O-a and P-a, respectively. P-a characterizing movements achieved higher inter-observer consistencies, while those characterizing body posture and interpretative movements were low. This exercise has: (1) provided feedback for software developers to further adapt the annotation software; (2) created the framework for describing disruptive behaviours using a neutral annotation language, and (3) was integrated into the IPSA-Video-Annotation-Training-Module. BC Children’s Hospital Research Institute and Foundation.
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 | 0.001 | 0.003 |
| 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 | 0.000 | 0.000 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.032 | 0.006 |
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".