Abstract
The “resect-and-discard” and “leave in situ” strategies for colorectal polyps, which were proposed to reduce polypectomy-related costs, are attracting great attention. 1 Rex D.K. et al. Gastrointest Endosc. 2011; 73: 419-422 Abstract Full Text Full Text PDF PubMed Scopus (435) Google Scholar The American Society for Gastrointestinal Endoscopy proposed diagnostic performance thresholds (negative predictive value or surveillance interval agreement ≥90%) for these optical biopsy strategies. 2 Rees C.J. et al. Gut. 2017; 66: 887-895 Crossref PubMed Scopus (120) Google Scholar Artificial intelligence (AI)–assisted computer-aided characterization (CADx) has been investigated as a possible solution for implementing optical biopsy strategies. 3 Chen P.J. et al. Gastroenterology. 2018; 154: 568-575 Abstract Full Text Full Text PDF PubMed Scopus (231) Google Scholar , 4 Byrne M.F. et al. Gut. 2019; 68: 94-100 Crossref PubMed Scopus (338) Google Scholar , 5 Misawa M. et al. Dig Endosc. 2021; 33: 273-284 Crossref PubMed Scopus (16) Google Scholar However, it remains uncertain how endoscopists interpret the output of CADx in clinical practice. We therefore conducted a prospective study to investigate the comprehensive diagnostic performance of endoscopists in relation to CADx predictions.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
