Premium
Development and validation of a radiomics signature as a non‐invasive complementary predictor of gastroesophageal varices and high‐risk varices in compensated advanced chronic liver disease: A multicenter study
Author(s) -
Huang Yifei,
Huang Fangze,
Yang Li,
Hu Weiling,
Liu Yanna,
Lin Zihuai,
Meng Xiangpan,
Zeng Manling,
He Chaohui,
Xu Qing,
Xie Guanghang,
Liu Chuan,
Liang Mingkai,
Li Xiaoguo,
Kang Ning,
Xu Dan,
Wang Jitao,
Zhang Liting,
Mao Xiaorong,
Yang Changqing,
Xu Ming,
Qi Xiaolong,
Mao Hua
Publication year - 2021
Publication title -
journal of gastroenterology and hepatology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.214
H-Index - 130
eISSN - 1440-1746
pISSN - 0815-9319
DOI - 10.1111/jgh.15306
Subject(s) - medicine , esophagogastroduodenoscopy , cohort , receiver operating characteristic , varices , confidence interval , radiology , gold standard (test) , prospective cohort study , endoscopy , gastroenterology , cirrhosis
Abstract Background and Aim Gastroesophageal varices (GEV) present in compensated advanced chronic liver disease (cACLD) and can develop into high‐risk varices (HRV). The gold standard for diagnosing GEV is esophagogastroduodenoscopy (EGD). However, EGD is invasive and less tolerant. This study aimed to develop and validate radiomics signatures based on noncontrast‐enhanced computed tomography (CT) images for non‐invasive diagnosis of GEV and HRV in patients with cACLD. Methods The multicenter trial enrolled 161 patients with cACLD from six university hospitals in China between January 2015 and September 2019, who underwent both EGD and noncontrast‐enhanced CT examination within 14 days prior to the endoscopy. Two radiomics signatures, termed r GEV and r HRV, respectively, were built based on CT images in a training cohort of 129 patients and validated in a prospective validation cohort of 32 patients (ClinicalTrials. gov identifier: NCT03749954). Results In the training cohort, both r GEV and r HRV exhibited high discriminative abilities on determining the existence of GEV and HRV with the area under receiver operating characteristic curve (AUC) of 0.941 (95% confidence interval [CI] 0.904–0.978) and 0.836 (95% CI 0.766–0.905), respectively. In validation cohort, r GEV and r HRV showed high discriminative abilities with AUCs of 0.871 (95% CI 0.739–1.000) and 0.831 (95% CI 0.685–0.978), respectively. Conclusions This study demonstrated that r GEV and r HRV could serve as the satisfying auxiliary parameters for detection of GEV and HRV with good diagnostic performance.