Computer-Aided Diagnosis for Leaving-in-situ of Colorectal Polyps: A systematic review and meta-analysis
Bibliographic record
Abstract
Aims Real-time computer-aided optical diagnosis (CADx) with artificial intelligence aims at assisting endoscopists to distinguish neoplastic from non-neoplastic diminutive rectosigmoid polyps during colonoscopy and thus reduce unnecessary removal of polyps. This systematic review and meta-analysis of accuracy studies aim to quantify the benefits and harms of CADx in colonoscopy. Methods We searched MEDLINE, EMBASE, and Scopus databases from inception until January 31, 2023. We included histologically-verified accuracy diagnostic studies that evaluated real-time performance of physicians in predicting neoplastic change of small ( < 5mm) rectosigmoid polyps without or with CADx assistance during colonoscopy. We estimated clinical benefit and harm based on accuracy values of the endoscopist before and after CADx assistance. Certainty of evidence was assessed with using the GRADE framework. The outcome measure for benefit was the proportion of polyps predicted as non-neoplastic that could avoid removal under the use of CADx. The outcome measure for harm was the proportion of neoplastic polyps that could be not resected and left-in-situ due to an incorrect diagnosis under the use of CADx. Histology served as ground-truth for both of the outcomes. Results Seven studies including 1,945 patients with 3,128 small rectosigmoid polyps were analyzed. The studies that assessed stand-alone performance of CADx (6 studies, 2,151 polyps) showed 89% (95% CI 84% – 94%) sensitivity and 85% (95% CI 73% – 97%) specificity in predicting neoplastic change. In the studies that compared histology prediction performance before and after the CADx assistance (3 studies, 1,770 polyps), there was no difference in the proportion of non-neoplastic polyps that could avoid removal (58% versus 61%; risk ratio 1.06, 95% CI 0.92 – 1.22; moderate certainty evidence). There was no difference in the proportion of neoplastic polyps that would be erroneously left-in-situ (8% versus 8%; risk ratio, 1.06, 95% CI 0.72 – 1.58; moderate certainty evidence). Conclusions CADx provided no incremental benefit nor harm in the management of small rectosigmoid polyps during colonoscopy. The limitation of our analysis was that most included studies were undergone on trained expert endoscopists, and the application of optical diagnosis was only simulated, potentially altering the decision making process of the operator. 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 | 0.005 | 0.020 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.010 | 0.016 |
| Bibliometrics | 0.003 | 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 | 0.001 |
| 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".