文献类型：期刊文献

英文题名：Real-Time Evaluation of Helicobacter pylori Infection by Convolution Neural Network During White-Light Endoscopy: A Prospective, Multicenter Study (With Video)

作者：Shen, Yuqin[1,2];Chen, Angli[3];Zhang, Xinsen[4];Zhong, Xingwei[5];Ma, Ahuo[6];Wang, Jianping[5];Wang, Xinjie[1];Zheng, Wenfang[7];Sun, Yingchao[1];Yue, Lei[1];Zhang, Zhe[8];Zhang, Xiaoyan[4];Lin, Ne[1];Kim, John J.[9];Du, Qin[10];Liu, Jiquan[4];Hu, Weiling[1]

机构：[1]Zhejiang Univ, Sir Run Run Shaw Hosp, Med Sch, Dept Gastroenterol, Hangzhou, Peoples R China;[2]Sichuan Univ, West China Xiamen Hosp, Xiamen, Peoples R China;[3]Shaoxing Univ, Sch Med, Shaoxing, Zhejiang, Peoples R China;[4]Zhejiang Univ, Coll Biomed Engn & Instrument Sci, Key Lab Biomed Engn, Minist Educ, Hangzhou, Peoples R China;[5]Deqing Cty Peoples Hosp, Dept Gastroenterol, Huzhou, Peoples R China;[6]Shaoxing Peoples Hosp, Dept Gastroenterol, Shaoxing, Peoples R China;[7]Hangzhou First Peoples Hosp, Dept Gastroenterol, Hangzhou, Peoples R China;[8]Longyou Cty Peoples Hosp, Dept Gastroenterol, Quzhou, Peoples R China;[9]Loma Linda Univ Hlth, Div Gastroenterol & Hepatol, Loma Linda, CA USA;[10]Zhejiang Univ, Affiliated Hosp 2, Med Sch, Dept Gastroenterol, Hangzhou, Peoples R China

年份：2023

卷号：14

期号：10

外文期刊名：CLINICAL AND TRANSLATIONAL GASTROENTEROLOGY

收录：SCI-EXPANDED(收录号：WOS:001158090200009)、、EI(收录号：20230098536)、Scopus(收录号：2-s2.0-85174640371)、WOS

基金：This work was supported by the Medical and Health Science and Technology Project of Zhejiang Province (grant no. 2020RC064), the Key R&D Program of Zhejiang Province (grant no. 2021C03111), and the National Natural Science Foundation of China (grant no. 81827804 and no. 31771072).

语种：英文

外文关键词：Helicobacter; H. pylori; convolutional neural network; real-time; artificial intelligence

外文摘要：INTRODUCTION: Convolutional neural network during endoscopy may facilitate evaluation of Helicobacter pylori infection without obtaining gastric biopsies. The aim of the study was to evaluate the diagnosis accuracy of a computer-aided decision support system for H. pylori infection (CADSS-HP) based on convolutional neural network under white-light endoscopy. METHODS: Archived video recordings of upper endoscopy with white-light examinations performed at Sir Run Run Shaw Hospital (January 2019-September 2020) were used to develop CADSS-HP. Patients receiving endoscopy were prospectively enrolled (August 2021-August 2022) from 3 centers to calculate the diagnostic property. Accuracy of CADSS-HP for H. pylori infection was also compared with endoscopic impression, urea breath test (URT), and histopathology. H. pylori infection was defined by positive test on histopathology and/or URT. RESULTS: Video recordings of 599 patients who received endoscopy were used to develop CADSS-HP. Subsequently, 456 patients participated in the prospective evaluation including 189 (41.4%) with H. pylori infection. With a threshold of 0.5, CADSS-HP achieved an area under the curve of 0.95 (95% confidence interval [CI], 0.93-0.97) with sensitivity and specificity of 91.5% (95% CI 86.4%-94.9%) and 88.8% (95% CI 84.2%-92.2%), respectively. CADSS-HP demonstrated higher sensitivity (91.5% vs 78.3%; mean difference 5 13.2%, 95% CI 5.7%-20.7%) and accuracy (89.9% vs 83.8%, mean difference 5 6.1%, 95% CI 1.6%-10.7%) compared with endoscopic diagnosis by endoscopists. Sensitivity of CADSS-HP in diagnosing H. pylori was comparable with URT (91.5% vs 95.2%; mean difference 5 3.7%, 95% CI 21.8% to 9.4%), better than histopathology (91.5% vs 82.0%; mean difference 5 9.5%, 95% CI 2.3%-16.8%). DISCUSSION: CADSS-HP achieved high sensitivity in the diagnosis of H. pylori infection in the real-time test, outperforming endoscopic diagnosis by endoscopists and comparable with URT. Clinicaltrials.gov; ChiCTR2000030724.