Background/Aims A large percentage of patients undergoing esophagogastroduodenoscopy (EGD) screening do not have esophageal varices (EV) or have only small EV. We evaluated a large, international, multicenter cohort to develop a novel score, termed FIB-4plus, by combining the fibrosis-4 (FIB-4) score, liver stiffness measurement (LSM), and spleen stiffness measurement (SSM) to identify high-risk EV (HRV) in compensated cirrhosis.
Methods This international cohort study involved patients with compensated cirrhosis from 17 Chinese hospitals and one Croatian institution (NCT04546360). Two-dimensional shear wave elastography-derived LSM and SSM values, and components of the FIB-4 score (i.e., age, aspartate aminotransferase, alanine aminotransferase, and platelet count [PLT]) were combined using machine learning algorithms (logistic regression [LR] and extreme gradient boosting [XGBoost]) to develop the LR-FIB-4plus and XGBoost-FIB-4plus models, respectively. Shapley Additive exPlanations method was used to interpret the model predictions.
Results We analyzed data from 502 patients with compensated cirrhosis who underwent EGD screening. The XGBoost-FIB-4plus score demonstrated superior predictive performance for HRV, with an area under the receiver operating characteristic curve (AUROC) of 0.927 (95% confidence interval [CI] 0.897–0.957) in the training cohort (n=268), and 0.919 (95% CI 0.843–0.995) and 0.902 (95% CI 0.820–0.984) in the first (n=118) and second (n=82) external validation cohorts, respectively. Additionally, the XGBoost-FIB-4plus score exhibited high AUROC values for predicting EV across all cohorts. The FIB-4plus score outperformed the individual parameters (LSM, SSM, PLT, and FIB-4).
Conclusions The FIB-4plus score effectively predicted EV and HRV in patients with compensated cirrhosis, providing clinicians with a valuable tool for optimizing patient management and outcomes.
Citations
Citations to this article as recorded by
The evolution of non-invasive strategies in cirrhosis management—from screening to precision monitoring: Editorial on “Fibrosis-4plus score: a novel machine learning-based tool for screening high-risk varices in compensated cirrhosis (CHESS2004): an inter Haiyu Wang, Jinjun Chen Clinical and Molecular Hepatology.2026; 32(1): 403. CrossRef
Metabolic factor-based machine learning model for mortality prediction in acute hepatitis E: Development and validation from a dual-center cohort Haoshuang Fu, Shuying Song, Yuelin Xiao, Bingying Du, Gangde Zhao, Tianhui Zhou, Yanan Du Digestive and Liver Disease.2026; 58(5): 660. CrossRef
Relative change rate of liver stiffness measurements predicts the risk of liver decompensation in compensated advanced chronic liver disease Yanqiu Li, Zihang Qiao, Jinze Li, Bingbing Zhu, Yu Lu, Ying Feng, Xianbo Wang Clinical and Experimental Medicine.2025;[Epub] CrossRef
Artificial Intelligence Applications in the Diagnosis and Management of Cirrhosis and Portal Hypertension: A Narrative Review Amrit Khooblall, Satish E. Viswanath, Layth Khawaja, Sameer Gadani Techniques in Vascular and Interventional Radiology.2025; 28(4): 101078. CrossRef
Liver stiffness measurement-based risk score for predicting liver decompensation risk: a single-center retrospective Chinese study Yanqiu Li, Zihang Qiao, Jinze Li, Yongqi Li, Ying Feng, Xianbo Wang Clinical and Experimental Medicine.2025;[Epub] CrossRef
Metabolomics and metabolites in cancer diagnosis and treatment Minyi Cai, Haiyan Liu, Chen Shao, Tingting Li, Jun Jin, Yahui Liang, Jinhu Wang, Ji Cao, Bo Yang, Qiaojun He, Xuejing Shao, Meidan Ying Molecular Biomedicine.2025;[Epub] CrossRef
Background/Aims Cholestatic liver diseases including primary biliary cholangitis (PBC) are associated with active hepatic fibrogenesis, which ultimately progresses to cirrhosis. Activated hepatic stellate cells (HSCs) are the main fibrogenic effectors in response to cholangiocyte damage. JCAD regulates cell proliferation and malignant transformation in nonalcoholic steatoheaptitis-associated hepatocellular carcinoma (NASH-HCC). However, its participation in cholestatic fibrosis has not been explored yet.
Methods Serial sections of liver tissue of PBC patients were stained with immunofluorescence. Hepatic fibrosis was induced by bile duct ligation (BDL) in wild-type (WT), global JCAD knockout mice (JCAD-KO) and HSC-specific JCAD knockout mice (HSC-JCAD-KO), and evaluated by histopathology and biochemical tests. In situ-activated HSCs isolated from BDL mice were used to determine effects of JCAD on HSC activation.
Results In consistence with staining of liver sections from PBC patients, immunofluorescent staining revealed that JCAD expression was identified in smooth muscle α-actin (α-SMA)-positive fibroblast-like cells and was significantly up-regulated in WT mice with BDL. JCAD deficiency remarkably ameliorated BDL-induced hepatic injury and fibrosis, as documented by liver hydroxyproline content, when compared to WT mice with BDL. Histopathologically, collagen deposition was dramatically reduced in both JCAD-KO and HSC-JCAD-KO mice compared to WT mice, as visualized by Trichrome staining and semi-quantitative scores. Moreover, JCAD deprivation significantly attenuated in situ HSC activation and reduced expression of fibrotic genes after BDL.
Conclusions JCAD deficiency effectively suppressed hepatic fibrosis induced by BDL in mice, and the underlying mechanisms are largely through suppressed Hippo-YAP signaling activity in HSCs.
Underestimated and Overlooked Factors in PBC Progression: Bacterial and Fungal Infections Yaxin Zhu, Sumeng Li, Shiqi Li, Yichen Wang, Yanqin Du, Xin Zheng, Jun Wu International Journal of Molecular Sciences.2026; 27(6): 2766. CrossRef
Activated hepatic stellate cells maintain hepatic bile acid homeostasis through paracrine FGF10/FGFR2 signaling Santie Li, Gaozan Tong, Mei Xue, Leyi Shen, Kunxuan Zhu, Jianjun Feng, Junfu Fan, Junjie Lu, Xiaojing Yi, Luhai Wang, Jiaqi Liang, Weitao Cong, Xiaokun Li Journal of Hepatology.2026; 85(2): 314. CrossRef
Integrating network pharmacology and experimental validation to uncover the therapeutic mechanisms of Chaigui decoction in Schistosoma japonicum-induced liver fibrosis Kaiyuan Deng, Xinyao Du, Qiao Liu, Zhi Lan, Fengning Wang, Yulin Cao, Song Xu, Xiaoli Deng, Xiang Wu, Guangjie Li, Yujiao Yang, Xin Wang, Fengyu Yang, Qingyuan Gu, Qingyang Yao, Liangzheng Zou, Wanning Wang, Mijia Yuan, Teng Zhong, Pei Huang, Yonghua Zhou Acta Tropica.2026; 280: 108160. CrossRef
From network prediction to in vivo validation: luteolin attenuates cholestatic liver injury in association with PI3K/Akt/GSK-3β signalling modulation Yuxin Wu, Shiji Gong, Xin Wu, Wei Wang, Dongming Zhang, Jianxin Jia Naunyn-Schmiedeberg's Archives of Pharmacology.2026;[Epub] CrossRef
Matrix stiffness may drive multi-cellular crosstalk via YAP signaling in biliary atresia liver fibrosis: a mechanistic review Jiwen Cheng Frontiers in Cell and Developmental Biology.2026;[Epub] CrossRef
Transient receptor potential channel 6 knockout ameliorates hepatic fibrosis by inhibiting the activation and proliferation of hepatic stellate cells Xixi Zeng, Yanhong Liao, Weiyi Cheng Journal of Gastroenterology and Hepatology.2025; 40(1): 294. CrossRef
Hepatic Stellate Cell TM4SF1 Accelerates Hepatic Fibrosis Progression via Interacting With the Tyrosine Kinase c-Src Shenglu Liu, Peng Tan, Jiatong Chen, Zhiwei Huang, Bingyu Ren, Zhonghao Jiang, Boyuan Gu, Wenhao Yu, Lei Sun, Yingjun Chen, Jian Ruan, Wenguang Fu Cellular and Molecular Gastroenterology and Hepatology.2025; 19(10): 101559. CrossRef
JCAD deficiency delayed liver regenerative repair through the Hippo–YAP signalling pathway Li Zhang, Yong‐Yu Yang, Li Xie, Yuan Zhou, Zhenxing Zhong, Jia Ding, Zhong‐Hua Wang, Yu‐Li Wang, Xiu‐Ping Liu, Fa‐Xing Yu, Jian Wu Clinical and Translational Medicine.2024;[Epub] CrossRef
JCAD, a new potential therapeutic target in cholestatic liver disease Byoung Kuk Jang Clinical and Molecular Hepatology.2024; 30(2): 166. CrossRef
Correspondence on Letter regarding “Both liver parenchymal and non-parenchymal cells express JCAD proteins under various circumstances” Byoung Kuk Jang Clinical and Molecular Hepatology.2024; 30(2): 297. CrossRef
Both liver parenchymal and non-parenchymal cells express JCAD protein under various circumstances Li Xie, Li Zhang, Hui Chen, Yong-Yu Yang, Jian Wu Clinical and Molecular Hepatology.2024; 30(2): 279. CrossRef
First
Prev
