Randomized controlled study of the prediction of diminutive/small colorectal polyp histology using didactic versus computer‐based self‐learning module in gastroenterology trainees
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 AND AIM: The aim of this randomized trial was to evaluate the performance of self-training versus didactic training in order to increase the diagnostic accuracy of diminutive/small colonic polyp histological prediction by trainees. METHODS: Sixteen trainees reviewed 78 videos (48 iSCAN-OE and 30 NBI) of diminutive/small polyps in a pretraining assessment. Trainees were randomized to receive computer-based self-learning (n = 8) or didactic training (n = 8) using identical teaching materials and videos. The same 78 videos, in a different randomized order, were assessed. The NICE (NBI International Colorectal Endoscopic) and SIMPLE (Simplified Identification Method for Polyp Labeling during Endoscopy) classification systems were used to classify diminutive/small polyps. RESULTS: A higher proportion of high-confidence predictions of polyps was made by the self-training group versus the didactic group using both the SIMPLE classification (77.1% [95% CI 73.4-80.3] vs 69.9% [95% CI 66.1-73.5%] [P = 0.005]) and the NICE classification (77% [95% CI 73.2-80.4%] vs 69.8% [95% CI 66-73.4%] [P = 0.006]). When using NICE, sensitivity of the self-training group compared with the didactic group was 72% versus 83% (P = 0.0005), and the accuracy was 66.1% versus 69.1%. The training improved the confidence of participants and SIMPLE was preferred over NICE. CONCLUSION: Self-learning for the prediction of diminutive/small polyp histology is a method of training that can achieve results similar to didactic training. Availability of adequate self-learning teaching modules could enable widespread implementation of optical diagnosis in clinical practice.
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) | 0.001 | 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