A novel endoscopic artificial intelligence system to assist in the diagnosis of autoimmune gastritis: a multicenter study

作者：Shurong Chen, Lan‐Ping Xu, Ting Li, Yi Chen, Lingling Yan, Jie Zhang, Xuefeng Zhou, Jiayi Wang, Tianlian Yan, Jinghua Wang, Xinjue He, Han Ma, Xuequn Zhang, Shenghua Zhu, Yizhen Zhang, Chengfu Xu, Jianguo Gao, Xia Ji, Dezhi Bai, Yuan Chen, Hongda Chen, Yini Ke, Lan Li, Chaohui Yu, Xin‐Li Mao · 发表于：Endoscopy · 年份：2024 · DOI：10.1055/a-2451-3071 · 被引用次数：23 · 研究领域：Helicobacter pylori-related gastroenterology studies、Gastrointestinal Bleeding Diagnosis and Treatment、Gastric Cancer Management and Outcomes

Background Autoimmune gastritis (AIG), distinct from Helicobacter pylori-associated atrophic gastritis (HpAG), is underdiagnosed due to limited awareness. This multicenter study aimed to develop a novel endoscopic artificial intelligence (AI) system for assisting in AIG diagnosis. Methods Patients diagnosed with AIG, HpAG, or nonatrophic gastritis (NAG), were retrospectively enrolled from six centers. Endoscopic images with relevant demographic and medical data were collected for development of the AI-assisted system based on a multi-site feature fusion model. The diagnostic performance of the AI model was evaluated in internal and external datasets. Endoscopists’ performance with and without AI support was tested and compared using Mann–Whitney U test. Heatmap analysis was performed to interpret AI model outputs. Results 18 828 endoscopy images from 1070 patients (294 AIG, 386 HpAG, 390 NAG) were collected. On testing datasets, AI identified AIG with 96.9 % sensitivity, 92.2 % specificity, and area under the receiver operating characteristic curve (AUROC) of 0.990 (internal), and 90.3 % sensitivity, 93.1 % specificity, and AUROC of 0.973 (external). The performance of AI (sensitivity 91.3 %) was comparable to that of experts (87.3 %) and significantly outperformed nonexperts (70.0 %; P = 0.01). With AI support, the overall performance of endoscopists was improved (sensitivity 90.3 % [95 %CI 86.0 %–93.2 %] vs. 78.7 % [95 %CI 73.6 %–83.2 %]; P = 0.008). Heatmap analysis reveal...