Original Investigation 

Gastroenterology and Hepatology

Computer-Assisted Colonoscopy in High–Adenoma Detection Rate Settings in a High-Risk Population: A Randomized Clinical Trial

Wen-Feng Hsu, Chen-Ya Kuo, Hsu-Heng Yen, et al

JAMA Netw Open 2026;9;(4):e264881. doi:10.1001/jamanetworkopen.2026.4881

Key Points

Question  Does the use of computer-aided detection (CAD) during colonoscopy improve adenoma detection within high–adenoma detection rate (ADR) settings in the context of fecal immunochemical test (FIT)–based screening?

Findings  In this randomized clinical trial of 1356 participants, CAD met noninferiority criteria for ADR. Significant increases occurred only in the exploratory FIT-positive subgroup, driven by detection of diminutive adenomas, and led to more intensive surveillance intervals based on US Multi-Society Task Force guidelines.

Meaning  CAD-assisted colonoscopy was noninferior to standard colonoscopy; however, detection gains involved mainly small lesions and increased intensive surveillance recommendations, while long-term clinical benefits remain uncertain.

Abstract

Importance  Computer-aided detection (CAD) systems can enhance adenoma detection, but their effectiveness in high-performance settings and among patients with positive fecal immunochemical test (FIT) results remains uncertain.

Objective  To evaluate the impact of CAD on adenoma detection in routine practice, focusing on patients with positive FIT results.

Design, Setting, and Participants  This multicenter, open-label, randomized clinical trial was conducted at 4 tertiary hospitals in Taiwan from February 23, 2022, to November 27, 2024. Adults aged 40 to 79 years who were scheduled for a colonoscopy owing to FIT positivity, symptoms, screening, or surveillance were randomized 1:1 to CAD-assisted or standard colonoscopy. Data were analyzed from December 1, 2024, to February 28, 2025.

Exposures  Colonoscopy performed with a real-time CAD system or standard high-definition colonoscopy.

Main Outcomes and Measures  The primary outcome was adenoma detection rate (ADR), defined as the proportion of patients with at least 1 histologically confirmed adenoma. Secondary outcomes included adenomas per colonoscopy (APC), sessile serrated lesion detection rate (SSLDR), and postpolypectomy surveillance intervals according to the US Multi-Society Task Force (USMSTF) and European Society of Gastrointestinal Endoscopy criteria.

Results  Of 1356 randomized participants (mean [SD] age, 60.0 [9.4] years; 678 [50.0%] female and 678 [50.0%] male), CAD-assisted colonoscopy met noninferiority criteria for ADR compared with standard colonoscopy (395 of 675 [58.5%] vs 363 of 681 [53.3%]; absolute difference, 5.2 percentage points [95% CI, −0.1 to 10.5 percentage points]). Superiority was not statistically significant. CAD significantly increased mean (SD) APC (1.41 [1.95] vs 1.20 [1.88]; P = .01), driven mainly by detection of diminutive adenomas. In exploratory analyses of 864 patients with FIT-positive findings, CAD significantly increased ADR (288 of 441 [65.3%] vs 243 of 423 [57.4%]; P = .02; adjusted odds ratio [AOR], 1.39 [95% CI, 1.05-1.86]) and APC (mean [SD], 1.64 [2.08] vs 1.39 [2.09]; P = .01). SSLDR did not differ between groups. Consequently, CAD led to more intensive surveillance recommendations under USMSTF criteria, particularly in patients with FIT-positive findings (58 of 441 [13.2%] vs 31 of 423 [7.3%]; AOR, 1.94 [95% CI, 1.22-3.09]).

Conclusions and Relevance  In this randomized clinical trial, CAD-assisted colonoscopy met noninferiority criteria for adenoma detection. Superiority was not statistically significant overall, with significant improvements limited to the exploratory FIT-positive subgroup, driven largely by diminutive adenomas. CAD also increased intensive surveillance assignments. The incremental benefit of CAD in reducing interval cancer risk requires further investigation.

Trial Registration  ClinicalTrials.gov Identifier: NCT03842059