Clin Mol Hepatol. 2025;31(3):881-898.
Fibrosis-4plus score: a novel machine learning-based tool for screening high-risk varices in compensated cirrhosis (CHESS2004): an international multicenter study.
제1저자 Bingtian Dong, Ruiling He, Shenghong Ju, Yuping Chen, Ivica Grgurevic, Jianzhong Ma, Ying Guo, Huizhen Fan, and Qiang Yan · 교신저자 김원, Xiaolong Qi
소속 (39)
- Liver Disease Center of Integrated Traditional Chinese and Western Medicine, Department of Radiology, Zhongda Hospital, Medical School, Southeast University, Nurturing Center of Jiangsu Province for State Laboratory of AI Imaging & Interventional Radiology (Southeast University), Basic Medicine Research and Innovation Center of Ministry of Education, Zhongda Hospital, Southeast University, State Key Laboratory of Digital Medical Engineering, Nanjing, China.
- Department of Ultrasound, The First Affiliated Hospital of Anhui Medical University, Hefei, China.
- Department of Ultrasound, Donggang Branch the First Hospital of Lanzhou University, Lanzhou, China.
- The First Clinical Medical College of Lanzhou University, Lanzhou, Lanzhou, China.
- Nurturing Center of Jiangsu Province for State Laboratory of AI Imaging & Interventional Radiology, Department of Radiology, Zhongda Hospital, Medical School, Southeast University, Nanjing, China.
- Department of Gastroenterology, Hepatology and Clinical Nutrition, University Hospital Dubrava, University of Zagreb School of Medicine and Faculty of Pharmacy and Biochemistry, Zagreb, Croatia.
- Department of General Surgery, The Third People's Hospital of Taiyuan, Taiyuan, China.
- Department of Hepatology, The Third People's Hospital of Taiyuan, Taiyuan, China.
- Department of Gastroenterology, Yichun People's Hospital, Yichun, China.
- Division of HPB Section Department of General Surgery, Huzhou Central Hospital, The Affiliated Central Hospital of Huzhou University, Huzhou, China.
- Department of Ultrasound, Zhongshan Hospital, Fudan University, Shanghai, China.
- Department of Gastroenterology, Hepatology and Clinical Nutrition, University Hospital Dubrava, Zagreb, Croatia.
- Department of Gastroenterology and Hepatology, University Hospital Center Split, Split, Croatia.
- Department of Ultrasound, Beijing Friendship Hospital, Capital Medical University, Beijing, China.
- Department of Ultrasound, The People's Hospital of Linxia, Linxia, China.
- Department of Gastroenterology, Hospital of Chengdu Office of People's Government of Tibetan Autonomous Region, Sichuan, China.
- Department of Gastroenterology, Guangxi Hospital Division of the First Affiliated Hospital, Sun Yat-sen University, Taiyuan, China.
- Department of Ultrasound, The Third People's Hospital of Taiyuan, Taiyuan, China.
- Department of Ultrasound, The First Hospital of Lanzhou University, Lanzhou, China.
- Department of Infectious Diseases, The First Hospital of Lanzhou University, Lanzhou, China.
- Huzhou Key Laboratory of Precision Medicine Research and Translation for Infectious Diseases, Huzhou Central Hospital, Huzhou, China.
- Department of Ultrasonography, Tianjin Second People's Hospital, Tianjin, China.
- Department of Infectious Disease, Zigong First People's Hospital, Zigong, China.
- Department of Ultrasound, Zigong First People's Hospital, Zigong, China.
- Department of Gastroscopy, Zigong First People's Hospital, Zigong, China.
- Department of Radiology, Zhejiang Key Laboratory of Imaging and Interventional Medicine, Lishui Central Hospital, Li Shui, China.
- Ultrasound Diagnosis Center, Shaanxi Provincial People's Hospital, Xi'an, China.
- Department of Ultrasound, Ditan Hospital, Capital Medical University, Beijing, China.
- Department of Gastroenterology, The Affiliated Hospital of Southwest Medical University, Luzhou, China.
- Department of Ultrasound, The Affiliated Hospital of Southwest Medical University, Luzhou, China.
- Department of Ultrasound, North China University of Science and Technology Affiliated Hospital, Tangshan, China.
- Department of Ultrasound, Jincheng People's Hospital, Jincheng, China.
- Department of Hepatology, The Sixth People's Hospital of Shenyang, Shenyang, China.
- Sensetime Research, Shanghai, China.
- Wuxi Hisky Medical Technologies Co., Ltd., Wuxi, China.
- Department of Medical and Marketing, Suzhou Hengrui Medical Devices Co., Ltd., Suzhou, China.
- Shenzhen New Industries Biomedical Engineering Co., Ltd., Shenzhen, China.
- Department General Internal Medicine (DAIM), Hospitals Hirslanden Bern Beau Site, Salem and Permanence, Bern, Switzerland.
- Department of Internal Medicine, Seoul National University College of Medicine, Seoul Metropolitan Government Boramae Medical Center, Seoul, Korea.
Abstract
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).
CONCLUSION 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.
Keywords
Diagnostic modelElasticity imaging techniquesEsophageal and gastric varicesMachine learning
Figures
그림 출처: PubMed Central 공개 논문 (PMC12260638)
Comment · 정정
Conflict of interest statement
Conflicts of Interest . The authors have no conflicts to disclose.
그 밖의 정보
- 출판 형태
- Journal Article, Multicenter Study
- 저널
- Clinical and molecular hepatology · eISSN 2287-285X
- 전자 출판
- 2025-02-05
- MeSH
- Humans · Liver Cirrhosis* / complications / diagnosis · Male · Female · Middle Aged · Esophageal and Gastric Varices* / diagnosis / etiology · Machine Learning* · ROC Curve · Elasticity Imaging Techniques · Aged · Alanine Transaminase / blood · Aspartate Aminotransferases / blood · Platelet Count · Area Under Curve · Spleen / pathology · Liver / pathology / diagnostic imaging · Adult · Severity of Illness Index · Endoscopy, Digestive System · Logistic Models
- Substances
- Alanine Transaminase · Aspartate Aminotransferases
- 연구비
- National Natural Science Foundation of China 92359304 · National Natural Science Foundation of China 82402413 · Key Research and Development Program of Jiangsu Province BE2023767a · Southeast University 3290002303A2 · Zhongda Hospital 2023YJXYYRCPY03 · Zhongda Hospital CZXM-GSP-RC125 · Zhongda Hospital CZXM-GSP-RC119 · China Postdoctoral Science Foundation 2024M750461 · Natural Science Foundation of Jiangsu Province BK20241681 · Health Research Program of Anhui AHWJ2023A30169
- 참고문헌
- 37편