Impact of study design on adenoma detection in the evaluation of artificial intelligence–aided colonoscopy: a systematic review and meta-analysis

Abstract

Background and AimsRandomized controlled trials (RCTs) have reported that artificial intelligence (AI) improves endoscopic polyp detection. Different methodologies, namely parallel and tandem designs, have been employed to evaluate the efficacy of AI-assisted colonoscopy in RCTs. Systematic reviews and meta-analyses have reported a pooled effect that includes both study designs. However, it is unclear whether there are inconsistencies in the reported results of these two designs. Here, we aimed to determine whether study characteristics moderate between-trial differences in outcomes when evaluating the effectiveness of AI-assisted polyp detection. MethodsA systematic search of Ovid MEDLINE, EMBASE, Cochrane Central, Web of Science, and IEEE Xplore was performed through March 1, 2023 for RCTs comparing AI-assisted colonoscopy with routine high-definition colonoscopy in polyp detection. Primary outcome of interest was the impact of study type on adenoma detection rate (ADR). Secondary outcomes included the impact of study type on adenomas per colonoscopy (APC) and withdrawal time, as well as the impact of geographical location, AI system, and endoscopist experience on ADR. Pooled event analysis was performed using a random effects model. ResultsTwenty-four RCTs involving 17413 colonoscopies (8680 AI assisted, 8733 non-AI assisted) were included. AI-assisted colonoscopy improved overall ADR; RR 1.24 [1.17-1.31], I2=53%, p<0.001. Tandem studies collectively demonstrated improved ADR in AI-aided colonoscopies (RR 1.18 [95% CI 1.08-1.30], I2=0%, p<0.001), as did parallel studies (RR 1.26 [1.17-1.35], I2=62%, p<0.001), with no statistical subgroup difference between study design. Both tandem and parallel study designs revealed improvement in APC in AI-aided colonoscopies, but this improvement was more marked among tandem studies (p<0.001). AI assistance significantly increased withdrawal times for parallel (p=0.002), but not tandem studies. ADR improvement was more marked among studies conducted in Asia compared to Europe and North America in a subgroup analysis (p=0.007). Type of AI system used or endoscopist experience did not impact overall improvement in ADR. ConclusionsEither parallel or tandem study design can capture the improvement in ADR resulting from the use of AI-assisted polyp detection systems. Tandem studies powered to detect differences in endoscopic performance through paired comparison may be a resource-efficient method of evaluating new AI-assisted technologies.