Commentary

Artificial intelligence (AI) is assumed to improve the detection of colorectal lesions, thus helping to reduce the risk of interval cancer after screening colonoscopy [1] [2] [3]. However, endoscopists need to be aware that AI systems should be used to assist and not to replace them. As a matter of concrete experience, this video underlines the crucial role of the endoscopist, who is ultimately in charge and responsible for detecting lesions underrepresented in AI training datasets (i. e., flat lesions such as sessile serrated lesions, and nongranular laterally spreading lesions) by performing a thorough and methodical inspection, using both proper mucosal exposure and applying human visual detection skills. In the future, the capability of AI systems to detect flat and subtle lesions will likely be improved, hopefully minimizing the risk of missing important premalignant lesions; however, we do not envisage a day when the role of the endoscopist becomes negligible.

Publication History

Article published online:
27 October 2022

• References

• 1 Rondonotti E, Di Paolo D, Rizzotto ER. et al.; AIFIT Study Group. Efficacy of a computer-aided detection system in a fecal immunochemical test-based organized colorectal cancer screening program: a randomized controlled trial (AIFIT study). Endoscopy 2022; 54 DOI: 10.1055/a-1849-6878.
• 2 Spadaccini M, Iannone A, Maselli R. et al. Computer-aided detection versus advanced imaging for detection of colorectal neoplasia: a systematic review and network meta-analysis. Lancet Gastroenterol Hepatol 2021; 10: 793-802 DOI: 10.1016/S2468-1253(21)00215-6.
• 3 Areia M, Mori Y, Correale L. et al. Cost–effectiveness of artificial intelligence for screening colonoscopy: a modelling study. Lancet Digit Health 2022; 6: e436-e444 DOI: 10.1016/S2589-7500(22)00042-5.