Effect of Computer-Aided Detection During Colonoscopy on Adenoma Detection Rate in a Community Hospital Setting: Randomized Controlled Trial.

Abstract

Objectives: Computer-aided detection (CADe) is promising for improving adenoma detection rates (ADRs) but mostly in academic centers. Therefore, we evaluated the effect of CADe on ADR and related outcomes in a Japanese community hospital setting.

Methods: In this single-center, randomized controlled trial conducted between September 2022 and August 2023, patients were eligible for inclusion if they were 40 years of age or older and had undergone colonoscopy for screening, post-polypectomy surveillance, a positive fecal immunochemical test, or symptoms. Patients were randomized at a 1:1 ratio to undergo colonoscopy with or without CADe. The primary outcome was ADR. Secondary outcomes included the number of adenomas per colonoscopy (APC) and the withdrawal time.

Results: A total of 1041 patients were recruited. After exclusion, 497 and 501 patients in the control and CADe groups, respectively, were included in the analysis. ADR was 54.5% in the control group and 50.7% in the CADe group, with no significant difference between the groups (adjusted risk ratio, 0.93; 95% confidence interval [CI], 0.83-1.05). The mean number of APC was lower in the CADe group than in the control group (1.34 vs. 1.14) (adjusted rate ratio, 0.86; 95% CI, 0.77-0.96). The mean withdrawal time was longer in the CADe group than in the control group (691 vs. 751 s, p = 0.034).

Conclusions: CADe did not significantly improve ADR in a Japanese community hospital setting, possibly due to the high baseline ADR in the control group. Further research is needed to understand in which settings CADe is useful.

Trial registration: University Hospital Medical Information Network Clinical Trials Registry: UMIN000049054.