Author commentary on Emanuele Rondonotti et al.

Emanuele Rondonotti et al. Artificial intelligence-assisted optical diagnosis for the resect-and-discard strategy in clinical practice: the Artificial intelligence BLI Characterization (ABC) study

Safe implementation of the resect-and-discard strategy for diminutive (≤ 5 mm) rectosigmoid polyps requires a high negative predictive value (NPV) of > 90% for optical diagnosis. This study shows that experts using AI-assisted optical diagnosis met NPV standards according to the ESGE and United States Multi-Society Task Force (USMSTF) guidelines; however, nonexperts did not meet these standards, although their performance improved over the course of the study.

Publication History

Article published online:
20 December 2022