Comparative efficacy of different computer-aided detection products in colonoscopy: a network meta-analysis of randomized controlled trials
Endoscopy · 13.10.2026
DOI: 10.1055/a-2936-2838 ↗Kurz gefasst
Netzwerk-Metaanalyse in der Zeitschrift Endoscopy, erschienen am 13.10.2026. Verfasst von Marcello Maida und 9 weiteren Autor:innen. Beteiligte Einrichtung: Kore University of Enna, Department of Medicine and Surgery, Italy, Enna. Die Arbeit nennt 68 Literaturangaben.
Abstract (Originalsprache)
Multiple computer-aided detection (CADe) systems have been developed to improve adenoma detection during colonoscopy, but their comparative efficacy and consistency of effect remain uncertain. This network meta-analysis aimed to compare the efficacy of different CADe systems across multiple detection outcomes. MEDLINE, Embase, Scopus, and the Cochrane library were systematically searched for randomized controlled trials (RCTs) comparing CADe-assisted colonoscopy versus colonoscopy without CADe or other CADe systems. The primary outcome was the adenoma detection rate (ADR). Secondary outcomes were adenomas per colonoscopy (APC) and the adenoma miss rate (AMR). A random-effects network meta-analysis was performed to synthesize direct and indirect evidence. 41 RCTs (31 789 patients; 14 CADe systems) were included. In the exploratory complete-network analysis, 10/14 systems significantly improved ADR (risk ratio [RR] 1.14–1.76), nine increased APC, and three reduced the AMR. In the FDA-cleared systems analysis, 3/6 improved ADR (RR 1.14–1.25), whereas three did not. Several systems retained a significant benefit in studies meeting the control-arm ADR thresholds recommended by ESGE (≥25%) and ASGE/ACG (≥35%), although effects varied across platforms and attenuation at higher baseline ADR was not uniform. Baseline ADR was not associated with treatment effects on meta-regression. The effectiveness of CADe-assisted colonoscopy is not uniform across platforms and varies according to the specific product. These findings support a system-specific rather than class-based evaluation of CADe technologies. However, comparative estimates should be interpreted cautiously given the low certainty of evidence for several outcomes and the absence of head-to-head comparisons and closed loops within the network.
Autor:innen und Institutionen
- Kore University of Enna, Department of Medicine and Surgery, Italy, Enna.
- Umberto I Hospital, Gastroenterology Unit, Italy, Enna.
- University of Naples Federico II, Department of Clinical Medicine and Surgery, Italy, Naples.
- The Chinese University of Hong Kong Faculty of Medicine, Department of Medicine and Therapeutics, Hong Kong, Hong Kong.
- The Chinese University of Hong Kong, Li Ka Shing Institute of Health Sciences, Hong Kong, Hong Kong.
- The Chinese University of Hong Kong, Institute of Digestive Diseases, Hong Kong, Hong Kong.
ORCID-Profile: Marcello Maida, Giulio Calabrese, Louis H S Lau, Giovanni Marasco, Sandro Sferrazza, Antonio Facciorusso, Cesare Hassan
Zitieren
APA
Maida, M., Calabrese, G., Lau, L. H. S., Qian, Z., Vitello, A., Marasco, G., Colecchia, L., Sferrazza, S., Facciorusso, A., & Hassan, C. (2026). Comparative efficacy of different computer-aided detection products in colonoscopy: a network meta-analysis of randomized controlled trials. Endoscopy. https://doi.org/10.1055/a-2936-2838
Vancouver
Maida M, Calabrese G, Lau LHS, Qian Z, Vitello A, Marasco G, et al. Comparative efficacy of different computer-aided detection products in colonoscopy: a network meta-analysis of randomized controlled trials. Endoscopy. 2026. doi:10.1055/a-2936-2838
BibTeX
@article{Maida2026,
author = {Maida, Marcello and Calabrese, Giulio and Lau, Louis H S and Qian, Zhouyao and Vitello, Alessandro and Marasco, Giovanni and Colecchia, Luigi and Sferrazza, Sandro and Facciorusso, Antonio and Hassan, Cesare},
title = {Comparative efficacy of different computer-aided detection products in colonoscopy: a network meta-analysis of randomized controlled trials},
journal = {Endoscopy},
year = {2026},
doi = {10.1055/a-2936-2838}
}
EUVIMED