A94 PRE-RESECTION OPTICAL EVALUATION RELIABLY DIFFERENTIATES BETWEEN SERRATED AND ADENOMATOUS LARGE NON-PEDUNCULATED COLORECTAL POLYPS
Bibliographic record
Abstract
Abstract Background Modality selection between cold snare resection (CSR) and endoscopic mucosal resection (EMR) or endoscopic submucosal dissection (ESD) is largely predicated on the ability to differentiate between serrated and adenomatous histopathology. While optical evaluation has modest accuracy for diminutive polyps, performance has not been evaluated for large non-pedunculated colorectal polyps (LNPCPs). Aims To evaluate the performance of pre-resection optical evaluation to differentiate between serrated and adenomatous LNPCPs. Methods Consecutive patients ampersand:003E 18 years of age who underwent endoscopic resection for a LNPCP were enrolled in a prospective single center observation cohort study (clinicaltrials.gov ID: NCT05402696). Pre-resection optical evaluation was performed using high-definition white-light and narrow-band imaging (NBI) with or without near-focus. The Japanese NBI Expert Team (JNET) classification was used to differentiate between serrated (JNET I) vs. adenomatous (JNET IIA, IIB) LNPCPs. Traditional serrated adenomas (TSAs) and cancers were excluded from analysis. Sensitivity, specificity, and accuracy were used to evaluate optical evaluation performance. Results From 06/2022-09/2023, 266 patients underwent 282 procedures for a total of 335 LNPCPs. Median size was 30mm (IQR 20-40mm). Histopathology identified 215 (64.2%) adenomatous, 91 (27.2%) serrated, 16 (4.8%) cancerous, and 13 (3.9%) other LNPCPs; including 5 TSAs. Of the 91 serrated lesions, 90 (98.9%) were predicted as serrated; sensitivity, specificity, and accuracy were 98.90% (95% CI 94.03-99.97), 99.53% (95% CI 97.44-99.99), 99.35% (95% CI 97.66-99.92), respectively. Of the 215 adenomatous lesions, 213 (99.1%) were predicted as adenomatous; sensitivity, specificity, and accuracy were 99.07% (95% CI 96.68-99.89), 98.90% (95% CI 94.03-99.97), 99.02% (95% CI 97.16-99.80), respectively. Conclusions Optical evaluation demonstrates excellent performance characteristics to differentiate between serrated and adenomatous LNPCPs; therefore, empowering endoscopists to reliably apply a selective resection algorithm between CSR, EMR and ESD. Funding Agencies None
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 | 0.003 |
| 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 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.003 | 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".