“…Research has highlighted promise of AI across gastroenterology, from analysing liver ultrasound images 5 to prognosticating in hepatocellular carcinoma, 6 and from personalising pancreatic cancer management 7 to predicting liver transplantation survival 8 . However, the impact of incorporating such algorithms into clinical workflows has not yet been robustly assessed 9 . Algorithms that perform well in retrospective studies can have a negative effect when implemented, as pointed out by the European Society of Gastrointestinal Endoscopy (ESGE) 10 .…”