Real-Time Computer-Aided Detection of Colorectal Neoplasia during Colonoscopy: Systematic review and meta-analysis
Bibliographic record
Abstract
Aims Artificial intelligence by computer-aided Detection (CADe) of colorectal neoplasia during colonoscopy may increase adenoma detection rates (ADR). We quantified benefit and harms of CADe in randomized trials. Methods We searched MEDLINE, EMBASE, and Scopus databases until September 2022 for randomized trials comparing CADe assisted with standard colonoscopy for polyp and cancer detection. Main outcome for CADe benefits were Per-patient and per-polyp adenoma detection rates (ADR), adenomas detected per colonoscopy (APC), Advanced Adenoma (>10 mm, high-grade dysplasia, villous histology), Serrated lesion (SPC). For CADe harms were number of polypectomies for non-neoplastic lesions and withdrawal time. Results Seventeen randomized trials on 16,024 patients were included. ADR was higher in theCADe group than in the standard group (45.,3% versus 37.,9%; RR 1.28 [95% CI 1.17-1.40];moderate low certainty evidence). The serrated lesion per-colonoscopywas also higher in the CADe group (MD, 0.028 [95% CI: 0.010; 0.046] moderate certaintyevidence). More non-neoplastic polyps were removed in the CADe than the standard group (0.4182vs. 0.282 per colonoscopy, MD: 0.1364; 95% CI, 0.063-0.2109; low certainty evidence) in a similarmean withdrawal time (MD: 0.36 minutes,95% CI, 0.04– 0.68, moderate certainty evidence). Conclusions The use of CADe for polyp detection during colonoscopy results in increased adenoma detection, but also higher rates of unnecessary removal non-neoplastic polyps Publication History Article published online: 14 April 2023 © 2023. European Society of Gastrointestinal Endoscopy. All rights reserved. Georg Thieme Verlag KG Rüdigerstraße 14, 70469 Stuttgart, Germany
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 | 0.011 | 0.034 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.011 | 0.019 |
| Bibliometrics | 0.002 | 0.004 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 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".