Prospective trial compares neoplasia detection rates in colorectal procedures, indicating AI has no significant advantage.
Background/Aims: Adenomas and sessile serrated lesions (SSLs) are neoplasms that play a role in colorectal cancer development. Improving adenoma detection rate (ADR) and SSL detection rates (SDR) allows for more effective prevention of colorectal cancer. Linked color imaging (LCI) and artificial intelligence (AI) have contributed to increased ADR and SDR. This study aimed to compare the neoplasia detection rates (NDR, adenomas, or SSLs) between LCI and AI-assisted LCI colonoscopy.Methods: We conducted a prospective randomized trial to compare LCI with LCI+AI. We evaluated ADR, SDR, and NDR as the primary outcomes.Results: A total of 779 polyps were detected in 622 patients (304 in the LCI group and 318 in the LCI+AI group); 555 were adenomas and 62 were SSLs for a total of 617 neoplastic lesions (79.2%) in 363 patients. Comparing the LCI and LCI+AI groups, the ADR, SDR, and NDR were 46.7% vs. 53.1% (p=0.13), 8.2% vs. 8.5% (p=0.90), and 52.3% vs. 56.6% (p=0.30), respectively. The mean number of adenomas per patient, advanced ADR, and withdrawal time did not significantly differ between the two groups.Conclusions: Similar results were observed in both groups, and even with the good performance of AI-assisted LCI, LCI alone yielded high ADR, SDR, and NDR.
No takes yet. Share an insight, caveat, or question.
Santos et al. (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: