Variability in Computer-Aided Detection effect on Adenoma Detection Rate in randomized controlled trials: a meta-regression analysis
Bibliographic record
Abstract
Aims The assistance of computer-aided detection (CADe) systems during colonoscopy may increase adenoma detection rate (ADR), theoretically reducing the risk of post-colonoscopy colorectal cancer (PCCRC). Although the promising results in different randomized trials, both the variability of the magnitude of relative effect of CADe systems across the previous studies, and the contradicting results in the first real-life experiences, highlighted a clear gap of knowledge when looking for those factors possibly explaining these fluctuating results. The aim of our analysis was to investigate the different variables possibly affecting the impact of CADe-assisted colonoscopy and its effect on ADR. Methods We searched MEDLINE, EMBASE, and Scopus databases until July 2023 for RCTs reporting diagnostic accuracy of CADe systems in the detection of colorectal neoplasia (PROSPERO: CRD42023462438). The main outcome was pooled adenoma detection rate (ADR). We calculated risk ratios (RRs), and performed meta-regression analysis to explore thesources of heterogeneity. The variables examined included factors with an impact on expected prevalence of adenomas across the study populations, such as gender, age and colonoscopy indication. We also included both key (ADR), and minor (Withdrawal time) performance measures considered as quality indicators for colonoscopy. Results Twenty-three randomized controlled trials (RCTs) on 19,077 patients were include. ADR was higher in the CADe group than in the standard colonoscopy group (45.83% versus 38.28%; RR 1.22 [95% CI 1.14-1.29]) with substantial level of heterogeneity (I 2 =67.69%). In univariable meta-regression analysis, patient age, ADR in control arms, and withdrawal time were the strongest predictors of CADe effect on ADR (P<.001), whereas FIT as an indication for colonoscopy was only suggestively associated with the outcome (P=0.098), and was included in the multivariable analysis. The proportion of male patients was not apparently associated with the CADe effect on ADR. In multivariable meta-regression, ADR in control arms, and withdrawal time were simultaneous significant predictors of the proportion of the CADe effect on ADR. Conclusions In conclusion, the substantial level of heterogeneity found appeared to be associated with variability in colonoscopy quality performances across the studies. As a matter of fact, across all the studies in which the CADe system showed no relative effect, the baseline ADR was higher than 60% suggesting a possible “ceiling effect” with little room left for improvement in the intervention group. On the other hand, endoscopists with lower quality performances are going to benefit the most from the use of CADe systems during colonoscopy, irrespectively from the expected adenoma prevalence across different populations. Thus, the implementation of CADe-assisted colonoscopy is supposed to help in reducing the gap in term of detection performances between high- and low- detectors. Publication History Article published online: 15 April 2024 © 2024. 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 | 0.071 | 0.130 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.013 | 0.046 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.004 | 0.002 |
| Open science | 0.003 | 0.001 |
| Research integrity | 0.003 | 0.004 |
| Insufficient payload (model declined to judge) | 0.004 | 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".