P188 Do you see what I see? An assessment of recognition and description of endoscopic inflammation by gastroenterology trainees and staff physicians
Bibliographic record
Abstract
Proficiency in endoscopy goes beyond technical competence; gastroenterologists should be able to accurately describe endoscopic findings and integrate them into management plans. The aim is to determine whether trainees and staff are describing inflammatory bowel disease (IBD) lesions in a similar manner, using available scoring systems and severity assessment measures. This cross-sectional questionnaire-based study recruited Gastroenterology trainees and staff across Canada (Mar-Oct 2017). Using 20 ileocolonoscopy images of single bowel segments, participants were asked to describe IBD inflammatory burden based physician severity rating, (PSR: healed, mild, moderate, severe), and then using the Mayo endoscopic score, MES (ulcerative colitis, UC) or the simple endoscopic score, SES-CD (Crohn’s disease, CD). Images were selected based on agreement by 3 IBD experts, who had rated them separately a priori, blinded to each other’s answers. Classic endoscopic findings of varying severity were presented (9 UC, 11 CD). Based on interpretation of endoscopic appearance, 10/20 images included a question on management. We examined inter-observer agreement among trainees and staff, compared trainees to staff, and determined accuracy of response by comparing both groups to the expert raters. 175 physicians participated: 129 staff and 46 trainees. For UC and CD, there was moderate inter-rater agreement using physician severity rating (K = 0.51 and 0.5 for staff, K = 0.46 and 0.41 for trainees). In UC, there was moderate inter-rater agreement for MES for staff and trainees: K = 0.47 and 0.44; in CD, the inter-rater agreement for SES-CD was only fair: K = 0.31 and 0.28 respectively. Compared with the experts, the mean accuracy score for UC was 72% for staff and 74% for trainees (p = 0.34); the mean score for CD was 77% and 63% respectively (p < 0.01). PSR accuracy scores were significantly higher than MES and SES-CD for staff (p < 0.01), but PSR and MES were equally accurate for trainees (p = 0.43). Trainees and staff better identified healed bowel/severe disease ( >75% accuracy for both) than mild or moderate disease (<65% accuracy, p < 0.05). There was a high agreement with experts on management ( >80%), though trainees consistently scored lower than staff (p < 0.01). In this real-world study, inter-rater agreement on description of ileocolonic lesions in IBD is moderate at best. Both staff and trainees can more accurately describe lesions in UC than in CD. Staff responses are more accurate using severity rating than scoring systems. Healed bowel or severe disease is more accurately described than mild/moderate disease. Further efforts are needed to identify the optimal means of standardising reporting IBD lesions.
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 | 0.002 | 0.011 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.007 | 0.002 |
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".