An interpretable artificial intelligence system for detecting risk factors of gastroesophageal variceal bleeding

Jing Wang; Zhengqiang Wang; Mingkai Chen; Yong Xiao; Shi Chen; Lianlian Wu; Liwen Yao; Xiaoda Jiang; Jiao Li; Ming Xu; Mengjuan Lin; Yijie Zhu; Renquan Luo; Chenxia Zhang; Xun Li; Honggang Yu

doi:10.1038/s41746-022-00729-z

An interpretable artificial intelligence system for detecting risk factors of gastroesophageal variceal bleeding

NPJ Digit Med. 2022 Dec 19;5(1):183. doi: 10.1038/s41746-022-00729-z.

Authors

Jing Wang^#^{1

2

3}, Zhengqiang Wang^#^{1

2

3}, Mingkai Chen^{1

2

3}, Yong Xiao^{1

2

3}, Shi Chen⁴, Lianlian Wu^{1

2

3}, Liwen Yao^{1

2

3}, Xiaoda Jiang^{1

2

3}, Jiao Li^{1

2

3}, Ming Xu^{1

2

3}, Mengjuan Lin^{1

2

3}, Yijie Zhu^{1

2

3}, Renquan Luo^{1

2

3}, Chenxia Zhang^{1

2

3}, Xun Li^{1

2

3}, Honggang Yu^{5

6

7}

Affiliations

¹ Department of Gastroenterology, Renmin Hospital of Wuhan University, Wuhan, China.
² Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision, Renmin Hospital of Wuhan University, Wuhan, China.
³ Key Laboratory of Hubei Province for Digestive System Disease, Renmin Hospital of Wuhan University, Wuhan, China.
⁴ Department of Gastroenterology, Wuhan Puren Hospital, Wuhan, China.
⁵ Department of Gastroenterology, Renmin Hospital of Wuhan University, Wuhan, China. yuhonggang@whu.edu.cn.
⁶ Hubei Provincial Clinical Research Center for Digestive Disease Minimally Invasive Incision, Renmin Hospital of Wuhan University, Wuhan, China. yuhonggang@whu.edu.cn.
⁷ Key Laboratory of Hubei Province for Digestive System Disease, Renmin Hospital of Wuhan University, Wuhan, China. yuhonggang@whu.edu.cn.

^# Contributed equally.

Abstract

Bleeding risk factors for gastroesophageal varices (GEV) detected by endoscopy in cirrhotic patients determine the prophylactical treatment patients will undergo in the following 2 years. We propose a methodology for measuring the risk factors. We create an artificial intelligence system (ENDOANGEL-GEV) containing six models to segment GEV and to classify the grades (grades 1-3) and red color signs (RC, RC0-RC3) of varices. It also summarizes changes in the above results with region in real time. ENDOANGEL-GEV is trained using 6034 images from 1156 cirrhotic patients across three hospitals (dataset 1) and validated on multicenter datasets with 11009 images from 141 videos (dataset 2) and in a prospective study recruiting 161 cirrhotic patients from Renmin Hospital of Wuhan University (dataset 3). In dataset 1, ENDOANGEL-GEV achieves intersection over union values of 0.8087 for segmenting esophageal varices and 0.8141 for gastric varices. In dataset 2, the system maintains fairly accuracy across images from three hospitals. In dataset 3, ENDOANGEL-GEV surpasses attended endoscopists in detecting RC of GEV and classifying grades (p < 0.001). When ranking the risk of patients combined with the Child‒Pugh score, ENDOANGEL-GEV outperforms endoscopists for esophageal varices (p < 0.001) and shows comparable performance for gastric varices (p = 0.152). Compared with endoscopists, ENDOANGEL-GEV may help 12.31% (16/130) more patients receive the right intervention. We establish an interpretable system for the endoscopic diagnosis and risk stratification of GEV. It will assist in detecting the first bleeding risk factors accurately and expanding the scope of quantitative measurement of diseases.