White light imaging versus artificial intelligence-assisted white light imaging for colorectal neoplasia detection: a randomised trial
Authors:
- Carlos Eduardo Oliveira dos SantosCSCarlos Eduardo Oliveira dos Santos
- Cadman LeggettCLCadman Leggett
- Prateek SharmaPSPrateek Sharma
- Gabriel Malaman dos SantosGSGabriel Malaman dos Santos
- Ivan David Arciniegas SanmartinISIvan David Arciniegas Sanmartin
- Júlio Carlos Pereira-LimaJPJúlio Carlos Pereira-Lima
Open Access
- 7 November 2025
- journal article
- research article
- Published by Sociedad de Gastroenterologia del Peru in Revista de Gastroenterología del Perú
- Vol. 45 (4) , 359-366
Abstract
Introduction: Adenoma detection rate (ADR) and sessile serrated lesion (SSL) detection rate (SDR) are crucial quality indicators for colonoscopy, as their improvement contributes to effective prevention of colorectal cancer. Artificial intelligence (AI) has been shown to significantly increase ADR. This study compared white light imaging (WLI) versus AI-assisted WLI for neoplasia detection. Materials and methods: This was a prospective, randomised trial of screening, surveillance, and symptomatic patients. Our primary objective was to evaluate ADR. Secondary objectives included SDR, mean number of adenomas per patient (MAP), neoplasia detection rate (NDR), advanced ADR (AADR), and colonoscope withdrawal time. Results: A total of 621 adenomas were diagnosed in 711 patients, with 310 adenomas in the WLI group and 311 adenomas in the WLI+AI group (p=0.65). Eighty-three SSLs and two intramucosal carcinomas were also detected, totalling 706 neoplasms. ADR was 45.9% in the WLI group and 50.8% in the WLI+AI group (p=0.20). ADR was 54.4% for screening, 49.0% for surveillance, and 40.0% for symptomatic patients (p=0.01). Marginal significance was observed in the WLI+AI group for screening patients (61.5% vs. 49.2%, p=0.06). SDR was 9.0% for both groups. MAP (0.9 vs. 0.9, p=0.34), NDR (51.0% vs. 56.8%, p=0.13), and AADR (8.4% vs. 7.6%, p=0.78) did not differ significantly between the groups. Withdrawal time was similar for the WLI (12.4±5.1 min) and WLI+AI (12.2±4.1 min) groups (p=0.32). Conclusions: AI-assisted colonoscopy demonstrated high ADR and NDR. While without statistical relevance overall, marginal significance was observed for screening patients.Keywords
This publication has 23 references indexed in Scilit:
- A comprehensive RCT in screening, surveillance, and diagnostic AI-assisted colonoscopies (ACCENDO-Colo study)Digestive and Liver Disease, 2025
- Effectiveness of artificial intelligence assisted colonoscopy on adenoma and polyp miss rate: A meta-analysis of tandem RCTsDigestive and Liver Disease, 2024
- Use of artificial intelligence improves colonoscopy performance in adenoma detection: a systematic review and meta-analysisGastrointestinal Endoscopy, 2024
- Quality indicators for colonoscopyGastrointestinal Endoscopy, 2024
- Single Versus Second Observer vs Artificial Intelligence to Increase the ADENOMA Detection Rate of Colonoscopy—A Network AnalysisDigestive Diseases and Sciences, 2024
- Impact of study design on adenoma detection in the evaluation of artificial intelligence–aided colonoscopy: a systematic review and meta-analysisGastrointestinal Endoscopy, 2024
- Efficacy of artificial intelligence in reducing miss rates of GI adenomas, polyps, and sessile serrated lesions: a meta-analysis of randomized controlled trialsGastrointestinal Endoscopy, 2024
- Cost-effectiveness of artificial intelligence for screening colonoscopy: a modelling studyThe Lancet Digital Health, 2022
- Comparison of efficacy of colonoscopy between the morning and afternoon: A systematic review and meta-analysisDigestive and Liver Disease, 2018
- Analysis of Administrative Data Finds Endoscopist Quality Measures Associated With Postcolonoscopy Colorectal CancerGastroenterology, 2011