Unified Magnifying Endoscopic Classification (UMEC) of Gastrointestinal Lesions: A North American Validation Study
Bibliographic record
Abstract
Background and study aim: Magnifying endoscopy enables the diagnosis of advanced neoplasia throughout the gastrointestinal tract. The unified magnifying endoscopic classification (UMEC) framework unifies optical diagnosis criteria in the esophagus, stomach, and colon, dividing lesions into three categories: non-neoplastic, intramucosal neoplasia, and deep submucosal invasive cancer. This study aims to ascertain the performance of North American endoscopists when using the UMEC. Methods: In this retrospective cohort study, five North American endoscopists without prior training in magnifying endoscopy independently diagnosed images of gastrointestinal tract lesions using UMEC. All endoscopists were blinded to endoscopic findings and histopathological diagnosis. Using histopathology as the gold standard, the endoscopists' diagnostic performances using UMEC were evaluated. Results: A total of 299 lesions (77 esophagus, 92 stomach, and 130 colon) were assessed. For esophageal squamous cell carcinoma, the sensitivity, specificity, and accuracy ranged from 65.2% (95%CI: 50.9-77.9) to 87.0% (95%CI: 75.3-94.6), 77.4% (95%CI: 60.9-89.6) to 96.8% (95%CI: 86.8-99.8), and 75.3% to 87.0%, respectively. For gastric adenocarcinoma, the sensitivity, specificity, and accuracy ranged from 94.9% (95%CI: 85.0-99.1) to 100%, 52.9% (95%CI: 39.4-66.2) to 92.2% (95%CI: 82.7-97.5), and 73.3% to 93.3%. For colorectal adenocarcinoma, the sensitivity, specificity, and accuracy ranged from 76.2% (95%CI: 62.0-87.3) to 83.3% (95%CI: 70.3-92.5), 89.7% (95%CI: 82.1-94.9) to 97.7% (95%CI: 93.1-99.6), and 86.8% to 90.7%. Intraclass correlation coefficients indicated good to excellent reliability. Conclusion: UMEC is a simple classification that may be used to introduce endoscopists to magnifying narrow-band imaging and optical diagnosis, yielding satisfactory diagnostic accuracy.
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 | 0.005 | 0.008 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".