Response to the Letter to the Editor: “AI-Assisted IBD Severity Classification: A Critical Perspective on Current Evidence and Next Steps”
Bibliographic record
Abstract
To the Editors, We appreciate the interest of Drs. Kumar, Mehta, and Sah in our recent publication “Artificial Intelligence for Classification of Endoscopic Severity of Inflammatory Bowel Disease: A Systematic Review and Critical Appraisal.”1 The following responses are offered. Application of artificial intelligence (AI) for the severity classification of Crohn’s disease (CD) is certainly complicated by the nature of the mucosal abnormalities seen on endoscopy. In CD, discontinuous lesions are seen throughout the gastrointestinal tract and are more heterogeneous than the comparatively uniform ulcerative colitis (UC) lesions. The ensuing challenges of lesion localization and location-based cumulative scoring may require creative machine-learning model design. In this respect, we are encouraged by the efforts that have already been demonstrated. Our original publication alludes to innovative approaches to characterizing full-length colonoscopy videos by groups like Fan et al., who developed an area-based score using the proportion of inflammation in each of the subdivided areas of the colon, and Higuchi et al., who generated topography maps of severity of the entire colorectum using capsule endoscopy.2,3 These approaches have been limited to UC to date but may inspire the design of models for severity grading of CD in future studies by providing a more holistic evaluation of the gastrointestinal tract rather than discrete snapshots.
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 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 | 0.001 | 0.007 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".