Shurong Chen et al. A novel endoscopic artificial intelligence system to assist in
the diagnosis of autoimmune gastritis: a multicenter study
An endoscopic artificial intelligence (AI) system was developed to assist the diagnosis
of autoimmune gastritis (AIG), using 18 828 endoscopy images from 1070 patients. On
an external testing dataset, the AI system identified AIG with a sensitivity of 90.3 %,
specificity of 93.1 %, and area under the receiver operating characteristic of 0.97.
AI performance was comparable to that of experts (87.3 %) and outperformed nonexperts
(70.0 %). Although future prospective studies are needed, the tool could be used for
guiding biopsy sampling and early detection of AIG.
