Artificial Intelligence-Assisted Colonoscopy for the Early Detection of Colorectal Neoplasia: A Systematic Review of Randomised Controlled Trials
Jurnal Locus Penelitian dan Pengabdian · 09.11.2026 · 5 (11) · 10093-10105
DOI: 10.58344/locus.v5i11.6486 ↗Kurz gefasst
Systematische Übersicht in der Zeitschrift Jurnal Locus Penelitian dan Pengabdian, online erschienen am 09.11.2026. Verfasst von OK Yulizal und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).
Abstract (Originalsprache)
This systematic review aimed to evaluate randomized controlled trials comparing artificial intelligence (AI)-assisted colonoscopy with standard colonoscopy for the detection of colorectal neoplasia and to assess the direction, magnitude, and consistency of effects across detection outcomes. Two independent reviewers searched PubMed/MEDLINE, Embase, Cochrane Central Register of Controlled Trials (CENTRAL), Scopus, and Web of Science from database inception through July 2026. They independently screened records, extracted data, and assessed the risk of bias using the Cochrane Risk of Bias 2 (RoB 2) tool. Randomized controlled trials involving adults that compared real-time computer-aided detection (CADe), with or without computer-aided diagnosis (CADx), against standard or sham-assisted colonoscopy were eligible for inclusion. Findings were synthesized narratively according to outcome domains, and the certainty of evidence was assessed using the Grading of Recommendations Assessment, Development and Evaluation (GRADE) approach. A quantitative meta-analysis was not performed because of clinical and methodological heterogeneity. Thirteen randomized controlled trials involving more than 12,000 participants were included, encompassing parallel-group and tandem designs and several commercially available CADe systems. The adenoma detection rate (ADR) was higher with CADe in most parallel-group trials, with statistically significant improvements observed in seven of ten trials and nonsignificant differences in the remaining three. Representative effect estimates included a risk ratio (RR) of 1.30 (95% confidence interval [CI], 1.14–1.45) and an adjusted odds ratio (aOR) of 1.47 (95% CI, 1.21–1.78). The mean number of adenomas detected per colonoscopy (APC) was consistently higher with CADe. In two tandem colonoscopy trials, the adenoma miss rate (AMR) was lower with CADe, including a reported rate of 15.5% versus 32.4% (aOR, 0.38; 95% CI, 0.23–0.62). However, the effects of CADe on advanced adenoma detection and sessile serrated lesion detection were less consistent.
Zitieren
APA
Yulizal, O., Anwar, D. D., & Lumantobing, C. J. E. (2026). Artificial Intelligence-Assisted Colonoscopy for the Early Detection of Colorectal Neoplasia: A Systematic Review of Randomised Controlled Trials. Jurnal Locus Penelitian dan Pengabdian, 5(11), 10093-10105. https://doi.org/10.58344/locus.v5i11.6486
Vancouver
Yulizal O, Anwar DD, Lumantobing CJE. Artificial Intelligence-Assisted Colonoscopy for the Early Detection of Colorectal Neoplasia: A Systematic Review of Randomised Controlled Trials. Jurnal Locus Penelitian dan Pengabdian. 2026;5(11):10093-10105. doi:10.58344/locus.v5i11.6486
BibTeX
@article{Yulizal2026,
author = {Yulizal, OK and Anwar, Dandy Daffa and Lumantobing, Christina J.R Esmeralda},
title = {Artificial Intelligence-Assisted Colonoscopy for the Early Detection of Colorectal Neoplasia: A Systematic Review of Randomised Controlled Trials},
journal = {Jurnal Locus Penelitian dan Pengabdian},
year = {2026},
volume = {5},
number = {11},
pages = {10093--10105},
doi = {10.58344/locus.v5i11.6486}
}
EUVIMED