Validation of a new optical diagnosis training module to improve dysplasia characterization in inflammatory bowel disease: a multicenter international study
Bibliographic record
Abstract
BACKGROUND AND AIMS: Inflammatory bowel disease (IBD) increases risk of dysplasia and colorectal cancer. Advanced endoscopic techniques allow for the detection and characterization of IBD dysplastic lesions, but specialized training is not widely available. We aimed to develop and validate an online training platform to improve the detection and characterization of colonic lesions in IBD: OPtical diagnosis Training to Improve dysplasia Characterization in Inflammatory Bowel Disease (OPTIC-IBD). METHODS: We designed a web-based learning module that includes surveillance principles, optical diagnostic methods, approach to characterization, and classifications of colonic lesions using still images and videos. We invited gastroenterologists from Canada, Italy, and the United Kingdom with a wide range of experience. Participants reviewed 24 educational videos of IBD colonic lesions, predicted histology, and rated their confidence. The primary endpoint was to improve accuracy in detecting dysplastic lesions after training on the platform. Furthermore, participants were randomized 1:1 to get additional training or not, with a final assessment occurring after 60 days. Diagnostic performance for dysplasia and rater confidence were measured. RESULTS: A total of 117 participants completed the study and were assessed for the primary endpoint. Diagnostic accuracy improved from 70.8% to 75.0% (P = .002) after training, with the greatest improvements seen in less experienced endoscopists. Improvements in both accuracy and confidence were sustained after 2 months of assessment, although the group randomized to receive additional training did not improve further. Similarly, participants' confidence in characterizing lesions significantly improved between before and after the course (P < .001), and it was sustained after 2 months of assessment. CONCLUSIONS: The OPTIC-IBD training module demonstrated that an online platform could improve participants' accuracy and confidence in the optical diagnosis of dysplasia in patients with IBD. The training platform can be widely available and improve endoscopic care for people with IBD. (Clinical trial registration number: NCT04924543.).
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 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".