A79 CLINICAL VALIDATION OF THE SIMPLE CLASSIFICATION FOR OPTICAL DIAGNOSIS OF DIMINUTIVE AND SMALL COLORECTAL POLYPS
Bibliographic record
Abstract
Abstract Background Image enhanced endoscopy (IEE) allows for real-time optical diagnosis of colorectal polyps in order to replace histopathology. A novel classification system (SIMPLE classification) has recently been developed for optical diagnosis when using the novel Pentax Optivista IEE platform. Aims The aim of this study was to evaluate the SIMPLE classification for optical polyp diagnosis in a prospective clinical study. Methods Patients undergoing screening, diagnostic or surveillance colonoscopies were enrolled in the study. All colorectal polyps 1-10mm found underwent optical polyp diagnosis using the SIMPLE classification with either iScan or Optivista for image-enhanced endoscopy (IEE). Polyps were resected as per standard care and sent for histopathology analysis. Optical diagnosis and surveillance intervals were calculated based on SIMPLE criteria and compared to pathology-based results as reference. Primary outcome was the agreement of the surveillance intervals based on the SIMPLE classification with pathology-based surveillance intervals for 1-5mm colorectal polyps. Secondary outcomes included negative predictive value (NPV) for rectosigmoid adenoma, percentage of pathology avoided, percentage of post-colonoscopy immediate recommendations, and surveillance interval agreement, rectosigmoid NPV for 1-10mm polyps. Results 399 patients (mean age: 62.4, 55.6% female) with 278 diminutive and 364 small polyps were evaluated in the study cohort. For ≤5mm polyps, agreement with pathology-based surveillance intervals was 93.5% [95% CI 91.1–95.9] (shorter: 4.5% [95% CI 2.5–6.5]; longer: 1.8% [95% CI 0.5–3.0]). NPV for rectosigmoid adenomatous polyps (including SSA) was 85.5% [95% CI 77.6–93.4]. Using Optical diagnosis and the SIMPLE classification, pathology analysis could be avoided in 61.5% [95% CI 56.9–66.2] of polyps and post-colonoscopy immediate surveillance interval recommendation could be given in 70.9% [95% CI 66.5–75.4] of patients. For ≤10mm polyps, agreement with pathology-based surveillance intervals was 92.2% [95% CI 89.6–94.9] (shorter: 5.5% [95% CI 3.3–7.8]; longer: 2.3% [95% CI 0.8–3.7]). NPV for rectosigmoid adenomatous polyps (including SSA) was 83.7% [95% CI 75.9–91.5]. Conclusions The first clinical validation study using the SIMPLE classification in combination with Optivista or iScan IEE showed a high (≥90%) surveillance interval agreement compared to pathology. More than 60% of pathology could be avoided, and most patients could be given immediate surveillance intervals when using IEE in combination with the SIMPLE classification. Funding Agencies NonePentax
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 | 0.008 | 0.025 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 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) | 0.002 | 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".