Efficacy of artificial intelligence for adenoma detection in water exchange colonoscopy: a two-center randomized controlled trial

Abstract

Water exchange and artificial intelligence-based computer-aided detection (CADe) separately improve the adenoma detection rate (ADR) and number of adenomas detected per colonoscopy (APC). We aimed to determine whether combining water exchange with CADe enhanced APC versus water exchange alone.This randomized controlled trial was conducted at hospitals in Italy and Taiwan using different CADe devices. Patients aged 45-75 years undergoing colonoscopy for screening, surveillance, or positive fecal blood tests were randomized to either water exchange with CADe assistance or water exchange alone. The primary outcome was APC, with 752 patients planned for randomization.An interim analysis was conducted on 560 patients (75% of the enrollment target; mean age 59.4 years; male 299; water exchange+CADe 279), with similar baseline characteristics between the two groups. APC was significantly higher with water exchange+CADe compared with water exchange alone (1.39 [95%CI 1.06-1.72] vs. 1.05 [95%CI 0.87-1.23]) with an incidence rate ratio of 1.32 (95%CI 1.14-1.54), representing an absolute increase of 0.34. The observed significant difference led to early trial termination. No significant differences were found in ADR and sessile serrated lesion detection rates between the groups (54.1% vs. 50.2% [P = 0.35] and 3.6% vs. 3.6% [P = 0.99], respectively), but this study was not powered to detect such differences. Withdrawal times and the mean number of non-neoplastic lesions per colonoscopy were comparable.For water exchange colonoscopy, integrating CADe statistically increased APC without prolonging withdrawal times or causing a concomitant increase in resection of non-neoplastic lesions.