Yifei Huang, Jia Li, Tianlei Zheng, Dong Ji, Yu Jun Wong, Hong You, Ye Gu, Musong Li, Lili Zhao, Shuang Li, Shi Geng, Na Yang, Guofeng Chen, Yan Wang, Manoj Kumar, Ankur Jindal, Wei Qin, Zhenhuai Chen, Yongning Xin, Zicheng Jiang, Xiaoling Chi, Jilin Cheng, Mingxin Zhang, Huan Liu, Ming Lu, Li Li, Yong Zhang, Chunwen Pu, Deqiang Ma, Qibin He, Shanhong Tang, Chunyan Wang, Shanghao Liu, Jitao Wang, Yanna Liu, Chuan Liu, Hao Liu, Shiv Kumar Sarin, Xiaolong Qi
BACKGROUND AND AIMS: The prevalence of high-risk varices (HRV) is low among compensated cirrhotic patients undergoing esophagogastroduodenoscopy (EGD). Our study aimed to identify a novel machine learning-based model, named ML EGD, for ruling out HRV and avoiding unnecessary EGDs in patients with compensated cirrhosis. METHODS: An international cohort from 17 institutions from China, Singapore, and India were enrolled (CHESS2001, NCT04307264). The variables with the top three importance scores (liver stiffness, platelet count, and total bilirubin) were selected by shapley additive explanation and inputted into light gradient boosting machine algorithm to develop ML EGD for identification of HRV...
October 14, 2022: Gastrointestinal Endoscopy