Endoscopic submucosal dissection and JNET classification for colorectal neoplasia: A North American academic center experience
Bibliographic record
Abstract
Abstract Objectives Endoscopic submucosal dissection (ESD) enables minimally invasive resection of superficial gastrointestinal neoplasms en bloc regardless of size. The Japan narrow band imaging expert team (JNET) classification utilizes optical magnification and narrow band imaging (NBI) to predict pathology. In North America, ESD is far from ubiquitous, and regional outcomes are not widely described. To date there are no North American studies describing the application and yield of the JNET classification as applied in the practice of ESD. Methods A retrospective, single‐center, cohort analysis was performed on a prospectively maintained database of ESD procedures. Between July 2016 and February 2023, all consecutive patients treated with ESD for colorectal lesions were identified and stratified by lesion location, JNET, NBI International Colorectal Endoscopic, lateral spreading tumors, and Paris classifications. Univariate analysis was used for clinicopathological data. p < 0.05 was considered statistically significant. Results A total of 112 patients were identified. One lesion, a lipoma, was excluded. Overall, 49.5% (55/111) of lesions were colonic and 50.5% (56/111) rectal. Most lesions were lateral spreading tumors (60.4%, 67/111). Overall, 96.4% (107/111) ESDs were successfully completed, 98.1% (105/107) en bloc, and 87.9% (94/107) R0. Adverse events occurred in 1.8% (2/111) of procedures. The median diameter was 4.0 cm and resected in a median time of 62.0 min. Overall, 70.1% (47/67) lesions were upstaged from pre‐ESD biopsy. JNET 2B showed 80.2% (95% CI 71.5–87.1) accuracy for high‐grade dysplasia or sm1. All JNET type 3 were ≥sm2 (p < 0.001). Conclusions ESD permits safe and effective resection of superficial colorectal neoplasms. JNET classification was more accurate than pre‐resection biopsy at predicting histology in this series.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 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".