Development and validation of the SIMPLE endoscopic classification of diminutive and small colorectal polyps
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
BACKGROUND: Prediction of histology of small polyps facilitates colonoscopic treatment. The aims of this study were: 1) to develop a simplified polyp classification, 2) to evaluate its performance in predicting polyp histology, and 3) to evaluate the reproducibility of the classification by trainees using multiplatform endoscopic systems. METHODS: In phase 1, a new simplified endoscopic classification for polyps - Simplified Identification Method for Polyp Labeling during Endoscopy (SIMPLE) - was created, using the new I-SCAN OE system (Pentax, Tokyo, Japan), by eight international experts. In phase 2, the accuracy, level of confidence, and interobserver agreement to predict polyp histology before and after training, and univariable/multivariable analysis of the endoscopic features, were performed. In phase 3, the reproducibility of SIMPLE by trainees using different endoscopy platforms was evaluated. RESULTS: = 0.002). The sensitivity, specificity, positive predictive value, and negative predictive value after training were 97 %, 88 %, 95 %, and 91 %. The interobserver agreement of polyp diagnosis improved from 0.46 (95 %CI 0.30 - 0.64) before to 0.66 (95 %CI 0.48 - 0.82) after training. The trainees demonstrated that the SIMPLE classification is applicable across endoscopy platforms, with similar post-training accuracies for narrow-band imaging NBI classification (0.69; 95 %CI 0.64 - 0.73) and SIMPLE (0.71; 95 %CI 0.67 - 0.75). CONCLUSIONS: Using the I-SCAN OE system, the new SIMPLE classification demonstrated a high degree of accuracy for adenoma diagnosis, meeting the ASGE PIVI recommendations. We demonstrated that SIMPLE may be used with either I-SCAN OE or NBI.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it