Deep Learning‐Based Prediction of High‐Risk Gastroesophageal Varices Using Two‐Dimensional Shear Wave Elastography

ABSTRACT Aims Bleeding from gastroesophageal varices (GEV) is a medical emergency associated with high mortality. We aim to construct an artificial intelligence‐based model of two‐dimensional shear wave elastography (2D‐SWE) of the liver and spleen to precisely assess the risk of GEV and high‐risk GEV (HRV). Methods This was a multicenter, prospective study conducted from October 2020 to September 2022 across 12 hospitals in China. Patients with compensated advanced chronic liver disease (cACLD) were enrolled, with informed consent obtained. A total of 1136 liver stiffness measurement (LSM) images and 1042 spleen stiffness measurement (SSM) images generated by 2D‐SWE. We leveraged deep learning methods to uncover associations between image features and patient risk; in this manner, we constructed models to predict GEV and HRV. Results A multimodality deep learning risk prediction (DLRP) model was constructed to assess GEV and HRV based on LSM and SSM images and clinical information. Validation analysis revealed that the area under the curve (AUC) values of DLRP were 0.91 for GEV (95% confidence interval [CI], 0.90–0.93, p < 0.05) and 0.88 for HRV (95% CI, 0.86–0.89, p < 0.01), which were significantly and robustly better than those of canonical risk indicators, including the values of LSM (0.63 and 0.68 for GEV and HRV) and SSM (0.75 for both GEV and HRV). Moreover, the DLRP model outperformed the model using individual parameters. In HRV prediction, the 2D‐SWE SSM images (0.75) were more informative than LSM (0.68, p < 0.01). Conclusion Our DLRP model shows excellent performance in predicting GEV and HRV, outperforming the canonical risk indicators LSM and SSM. Additionally, the 2D‐SWE SSM images provided more information and thus better accuracy in HRV prediction than the LSM images. Trial Registration ClinicalTrials.gov; NCT04546360.

Authors

Institutions

Publication Details

Journal
Portal hypertension & cirrhosis
Published
2025-08-18
DOI
https://doi.org/10.1002/poh2.70016
Primary Topic
Gastroesophageal reflux and treatments
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Deep Learning‐Based Prediction of High‐Risk Gastroesophageal Varices Using Two‐Dimensional Shear Wave Elastography

Xiaolong Qi, Chaofei Gao, Muhan Lv, Yunfang Liu et al.
Portal hypertension & cirrhosis
Gastroesophageal reflux and treatments
article

Deep Learning‐Based Prediction of High‐Risk Gastroesophageal Varices Using Two‐Dimensional Shear Wave Elastography

Xiaolong Qi, Chaofei Gao, Muhan Lv, Yunfang Liu, Li Bian, Linxue Qian, Wei Rao, Lan Wang, Juan Tang, Tingyu Wang, Jiansong Ji, Xiaomei Chen, Ruiling He, Xin Li, Peng Zhang, Wei Liu, Shaoting Zhang, Lili Zhao, Jinhua Shao, Xin Zhang, Xuemei Wang, Xinyu Zhang, Shu‐Hua Zhang, Jia Wang, Yao Zhang, Yin Li, Kun Wang, Yihua Wang, Yang Liu, Ping An, Jiaojiao Xu, Qiong Yan, Hui Huang, Meiqin Su, Guo Zhang, Yanni Liu, Fei Chen, Zhongwei Zhao, Shaoping Li, Fanbin He, Zhengzi Geng, Tao Ren, Kaiqiang Tang, Yunxiao Liang, Wenjuan Wang, Yonghe Zhou, Fang Ai, Yanqing Huang, Liting Zhang, Liyun Zheng, Бо Лю
article en

Abstract

ABSTRACT Aims Bleeding from gastroesophageal varices (GEV) is a medical emergency associated with high mortality. We aim to construct an artificial intelligence‐based model of two‐dimensional shear wave elastography (2D‐SWE) of the liver and spleen to precisely assess the risk of GEV and high‐risk GEV (HRV). Methods This was a multicenter, prospective study conducted from October 2020 to September 2022 across 12 hospitals in China. Patients with compensated advanced chronic liver disease (cACLD) were enrolled, with informed consent obtained. A total of 1136 liver stiffness measurement (LSM) images and 1042 spleen stiffness measurement (SSM) images generated by 2D‐SWE. We leveraged deep learning methods to uncover associations between image features and patient risk; in this manner, we constructed models to predict GEV and HRV. Results A multimodality deep learning risk prediction (DLRP) model was constructed to assess GEV and HRV based on LSM and SSM images and clinical information. Validation analysis revealed that the area under the curve (AUC) values of DLRP were 0.91 for GEV (95% confidence interval [CI], 0.90–0.93, p < 0.05) and 0.88 for HRV (95% CI, 0.86–0.89, p < 0.01), which were significantly and robustly better than those of canonical risk indicators, including the values of LSM (0.63 and 0.68 for GEV and HRV) and SSM (0.75 for both GEV and HRV). Moreover, the DLRP model outperformed the model using individual parameters. In HRV prediction, the 2D‐SWE SSM images (0.75) were more informative than LSM (0.68, p < 0.01). Conclusion Our DLRP model shows excellent performance in predicting GEV and HRV, outperforming the canonical risk indicators LSM and SSM. Additionally, the 2D‐SWE SSM images provided more information and thus better accuracy in HRV prediction than the LSM images. Trial Registration ClinicalTrials.gov; NCT04546360.

Portal hypertension & cirrhosisVol. 4(3)
Hebei Medical University (CN), Shanxi Medical University (CN), Capital Medical University (CN), Nanjing University of Information Science and Technology (CN), Wenzhou Medical University (CN), Affiliated Hospital of Southwest Medical University (CN), Shenzhen Metro (China) (CN), Shaanxi Provincial People's Hospital (CN), Sensimetrics Corporation (US), Ruian People's Hospital (CN), Zhongda Hospital Southeast University (CN), North China University of Science and Technology Affiliated Hospital (CN), Tianjin People's Hospital (CN), Xingtai People's Hospital (CN), The People's Hospital of Guangxi Zhuang Autonomous Region (CN), Zoucheng People's Hospital (CN), The People's Hospital of LinXia (CN), Group Sense (China) (CN), Shanxi Jincheng Anthracite Mining Group (China) (CN), Tibet Autonomous Region People's Hospital (CN), Xian Yang Central Hospital (CN), Beijing Friendship Hospital (CN), Jiangsu Hengrui Medicine (China) (CN), Beijing Ditan Hospital (CN), Zigong First People's Hospital (CN), Wuxi People's Hospital (CN), The Sixth People's Hospital of Shenyang (CN), Fourth People's Hospital of Taiyuan (CN), Shanxi Provincial People’s Hospital (CN), First Hospital of Lanzhou University (CN), Lanzhou University (CN), Nanjing University (CN), Tsinghua University (CN)
National Natural Science Foundation of China, China Postdoctoral Science Foundation, Government of Jiangsu Province, Natural Science Foundation of Jiangsu Province, Southeast University
Good health and well-being
Openalex Percentile: Top 68%
Gastroesophageal reflux and treatments
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.