Koh F.H.Li J.W.Wong S.H.Lee J.John S.Chong V.H.Wu K.c.Lui R.Ng S.S.M.Lam T.Y.T.Lau L.H.S.Makharia G.K.Abdullah M.Maulahela H.Kobayashi N.Sekiguchi M.Byeon J.S.Kim H.s.Lee Y.Y.Chiu H.M.Wu I.C.Leelakusolvong S.Sharma P.Lieberman D.Sung J.J.Y.Mahidol University2025-07-012025-07-012025-01-01Igie (2025)https://repository.li.mahidol.ac.th/handle/20.500.14594/111039Background and Aims: Artificial intelligence (AI)-assisted colonoscopy has been widely investigated for colorectal adenoma and cancer detection and characterization. However, clinical guidance on its use in colorectal cancer (CRC) screening and surveillance is lacking. In this study, we developed consensus guiding when and how to use AI-assisted colonoscopy in the daily practice of screening and surveillance of colorectal neoplasia. Methods: Experts from 12 Asian-Pacific countries and regions together with 4 international experts developed a set of consensus statements based on existing clinical evidence using the modified Delphi process. Results: Based on existing evidence, computer-assisted detection should be evaluated for use if available and deemed cost-effective as an adjunct to conventional colonoscopy for CRC screening. Computer-assisted diagnosis may be used for characterization of polyps but is not yet considered sufficient to determine if a polyp is neoplastic and needs to be removed. Computer-assisted quality assurance is generally welcome to improve the quality of colonoscopy. Early engagement of patients and nurses and training of endoscopists to use AI-assisted colonoscopy are crucial for the successful implementation. Conclusions: More validation studies on AI-assisted colonoscopy need to be done while AI technologies continue to improve.MedicineArticleSCOPUS10.1016/j.igie.2025.04.0012-s2.0-10500858014429497086