A78 COMPARISON OF THE NICE, SANO, AND WASP CLASSIFICATIONS FOR OPTICAL DIAGNOSIS OF SMALL COLORECTAL POLYPS
Bibliographic record
Abstract
Abstract Background Optical diagnosis can be used as an alternative to pathology for the evaluation of colorectal polyps. There exist multiple classification systems that can be used to assist in performing optical diagnosis. Aims The aim of this study was to compare three different optical diagnosis classifications (NICE, SANO and WASP) when using Optivista and iScan image enhanced endoscopy (IEE). Methods The study included subjects between 45–80 years undergoing an elective screening, surveillance, or diagnostic colonoscopy with optical diagnosis using Optivista or iScan IEE. Three validated IEE scales (NICE, SANO and WASP classifications) were used for all optical diagnoses. Primary outcome was the agreement with pathology for surveillance intervals determined when using NICE, SANO and WASP for polyps 1-10mm. Secondary outcomes for polyps 1-10mm included accuracy of polyp diagnosis and negative predictive value (NPV) for rectosigmoid adenomas. Results A total of 399 patients were prospectively enrolled in the trial. The polyp detection and adenoma detection rates were 58.6% and 38.8% respectively. The proportion of correct surveillance interval assignment when at least one optical diagnosis was made was 92.9% when using NICE, 92.3% when using SANO, 89.5% when using WASP (p=0.656). Correct diagnosis was made for 74.2% of polyps when using NICE, 74.2% when using SANO, 65.6% when using WASP (p=0.012). The NPV for rectosigmoid adenomas was 91.2% when using NICE, 90.5% when using SANO, 87.5% when using WASP. Conclusions For optical diagnosis using Optivista and iScan IEE, all studied classifications performed equally for surveillance interval assignment. WASP had lower proportion of correct diagnoses on a polyp level and lower NPV for rectosigmoid adenomas. 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 | 0.010 | 0.031 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| 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".