P127 Optical diagnosis training to improve dysplasia characterisation in inflammatory bowel disease (OPTIC-IBD): a multicentre RCT
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
<h3>Introduction</h3> Endoscopic surveillance is performed in inflammatory bowel disease (IBD) to detect dysplasia. However, chronic inflammation alters mucosal and vascular colonic architecture, complicating lesion recognition. Optical diagnosis enhances our ability to accurately characterise IBD-associated dysplasia but such training is not readily available. We aim to fill this gap by developing and validating the new OPTIC-IBD online training platform (NCT04924543, funding GutsUK TRN2019-03). <h3>Methods</h3> We designed an interactive, self-directed, multi-modality learning module. This includes surveillance principles, optical diagnosis methods, characterisation approach, classifications (SCENIC, Kudo, FACILE), examples and self-assessments. We invited participants from Canada, Italy and UK, including novice (<100 lifetime colonoscopies), intermediate and experienced endoscopists (≥1000). Assessments comprised 24 short endoscopic videos of IBD colonic lesions, divided into 8 non-dysplastic and 16 dysplastic lesions. Participants classified lesions, predicted histology and rated their confidence. All participants completed online training and feedback. Videos were repeated in a random order after ≥7 days. Participants were then randomised 1:1 to get feedback and extra training. All had a final assessment at 60 days with prior/new videos and similar case mix. We report diagnostic performance for dysplasia, interrater reliability and rater confidence. <h3>Results</h3> We present a planned interim analysis of 77 participants after pre- and post-course assessments (table 1). Diagnostic accuracy improved (primary endpoint: 44.5 to 54.0%, <i>P</i><0.0001), particularly for novice and intermediate endoscopists. Sensitivity for dysplasia increased (50.3 to 59.1%) in line with prior experience. Specificity and accuracy were most improved for high confidence diagnoses (44.9 to 70.3% and 55.0 to 64.6%). In multilevel logistic regression, training was associated with correct diagnoses for high confidence (OR 1.40, 1.13–1.77) but not low confidence ratings (OR 1.09, 0.96–1.25). Training improved precision between participants and their confidence. <h3>Conclusions</h3> The OPTIC-IBD training module improved participants’ accuracy, precision and confidence in the optical diagnosis of IBD-associated dysplasia.
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.
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 | 0.000 | 0.000 |
| 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 it