P0390 Development, internal, and external validation of a novel endoscopic activity score for evaluation of Crohn’s disease (EASE-CD)
Bibliographic record
Abstract
Abstract Background Endoscopy is essential for measuring luminal disease activity in Crohn’s disease (CD). Current endoscopic indices for evaluating CD activity are limited: they are only modestly correlated with disease activity, contain items that are ambiguously defined and have poor inter-observer reliability, and lack validated definitions for clinically relevant change. We aimed to develop and internally and externally validate a reliable and responsive endoscopic CD activity index. Methods In this multi-part study, candidate endoscopic items for index development with face validity derived from a prior RAND/UCLA appropriateness exercise were assessed by blinded central readers using ileocolonoscopy videos from the phase 3b adalimumab EXTEND (NCT00348283) and phase 2 risankizumab (NCT02031276) trials. Acceptable item-level operating properties for further consideration as covariables in regression for model building included at least moderate inter-rater reliability (intraclass correlation coefficient [ICC]≥0.41), and medium responsiveness defined as the probability of a patient receiving active treatment having a better endoscopy score than a patient receiving placebo or win probability (WinP) ≥0.56. Model development and internal validation with bootstrapping utilised data from 112 paired baseline and post-treatment videos from the adalimumab trial. External model validation utilised data from 108 video pairs from the risankizumab trial. Results The Endoscopic Activity Score for Evaluating CD (EASE-CD) is comprised of ulcer size, presence of deep ulcer(s), and percentage of ulcerated surface with each item evaluated and averaged across visualised bowel segments (Table 1). Total scores range from 0-100 (higher scores indicate greater endoscopic activity). EASE-CD demonstrated almost perfect inter-rater reliability (ICC 0.820 [95% CI: 0.662-0.906]) and a large degree of responsiveness (WinP 0.769 [95% CI: 0.658-0.851]). A 10-point reduction in EASE-CD had 87.8% specificity and 60.9% sensitivity for endoscopic response defined by the Simple Endoscopic Score for CD (SES-CD)/CD Endoscopic Index of Severity (CDEIS). Ulcer-free endoscopic remission results in EASE-CD=0. Conclusion EASE-CD is a novel, validated, continuous measure of endoscopic CD activity constructed using modern principles of index development, that is reliable, responsive to treatment, and linearly correlated with disease activity. EASE-CD does not include “narrowing” (which cannot be reliably evaluated between observers) or “affected area” (which is ambiguous in meaning, poorly reliable, and not independently associated with disease activity). EASE-CD is based only on ulcer-related items, the hallmark lesion in CD.
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 | 0.069 | 0.073 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 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".