Colorectal mucosal exposure area assessment using artificial intelligence: a multicenter prospective observational study
Bibliographic record
Abstract
Background: This study proposed a new quality control indicator for colonoscopy, the cumulative colorectal mucosal exposure area (CCMEA), to assess mucosal exposure, constructed a CCMEA system based on deep learning, and validated the indicator in a multicenter prospective observational study. Methods: The CCMEA system was based on ResNet50 and UNet++. A CCMEA threshold was determined on the basis of an adenoma detection rate (ADR) of 25%. A multicenter prospective observational study was conducted to evaluate the system and the threshold in clinical practice. Based on the CCMEA threshold, patients were divided into qualified and unqualified colonoscopy groups. The ADR and other lesion detection rates were then compared between the two groups. Results: 510 participants who underwent colonoscopy were evaluated, being grouped as having qualified (n = 270) or unqualified (n = 240) colonoscopies based on a CCMEA qualification threshold of 2000. The ADR was 39.5 percentage points higher in the qualified group than in the unqualified group (53.7% vs. 14.2%; adjusted odds ratio [aOR] 8.0, 95%CI 5.0–12.8; P < 0.001), and notably was higher for lesions ≤5 mm (42.2% vs. 10.0%; aOR 6.9, 95%CI 4.1–11.5; P < 0.001). The qualified group also had a significantly higher polyp detection rate (89.6% vs. 40.0%; aOR 13.1, 95%CI 7.8–21.8; P < 0.001) and higher mean numbers of both adenomas (1.0 vs. 0.2; adjusted incident rate ratio [aIRR] 5.9, 95%CI 4.3–8.4; P < 0.001) and polyps (5.8 vs. 1.3; aIRR 4.0, 95%CI 3.5–4.5; P < 0.001). Conclusions: The CCMEA qualified group, based on a CCMEA threshold of 2000, showed a higher ADR than the unqualified group, indicating CCMEA could be a promising colonoscopy quality indicator.
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 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".