Computer-Aided Diagnosis for Leaving-in-situ of Colorectal Polyps: A systematic review and meta-analysis
Endoscopy · 01.04.2024 · 56 (S 02 S 02) · S146
DOI: 10.1055/s-0044-1783008 ↗Kurz gefasst
Systematische Übersicht in der Zeitschrift Endoscopy, erschienen am 01.04.2024. Verfasst von T. Rizkala und 26 weiteren Autor:innen.
Abstract (Originalsprache)
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
Zitieren
APA
Rizkala, T., Hassan, C., Misawa, M., Yuichi, M., Facciorusso, A., Antonelli, G., Spadaccini, M., Houwen, B. B., Emanuele, R., Patel, H., Khalaf, K., Fernández, E. G., Pradeep, B., Dekker, E., Capogreco, A., A, G. S., Berzin, T., Li, J. W., Per, O. V., …, & Repici, A. (2024). Computer-Aided Diagnosis for Leaving-in-situ of Colorectal Polyps: A systematic review and meta-analysis. Endoscopy, 56(S 02 S 02), S146. https://doi.org/10.1055/s-0044-1783008
Vancouver
Rizkala T, Hassan C, Misawa M, Yuichi M, Facciorusso A, Antonelli G, et al. Computer-Aided Diagnosis for Leaving-in-situ of Colorectal Polyps: A systematic review and meta-analysis. Endoscopy. 2024;56(S 02 S 02):S146. doi:10.1055/s-0044-1783008
BibTeX
@article{Rizkala2024,
author = {Rizkala, T. and Hassan, C. and Misawa, M. and Yuichi, M. and Facciorusso, A. and Antonelli, G. and Spadaccini, M. and Houwen, B. B. and Emanuele, R. and Patel, H. and Khalaf, K. and Fernández, E.M. G. and Pradeep, B. and Dekker, E. and Capogreco, A. and A, G. Seth and Berzin, T. and Li, J. Weiquan and Per, O. V. and Sultan, S. and Menini, M. and Schilirò, A. and Roberta, M. and Douglas, K. R. and Prateek, S. and Farid, F. and Repici, A.},
title = {Computer-Aided Diagnosis for Leaving-in-situ of Colorectal Polyps: A systematic review and meta-analysis},
journal = {Endoscopy},
year = {2024},
volume = {56},
number = {S 02 S 02},
pages = {S146},
doi = {10.1055/s-0044-1783008}
}
EUVIMED