Machine learning based CAGIB score predicts in-hospital mortality of cirrhotic patients with acute gastrointestinal bleeding

Abstract Acute gastrointestinal bleeding (AGIB) is a potentially lethal complication in cirrhosis. In this prospective international multi-center study, the performance of CAGIB score for predicting the risk of in-hospital death in 2467 cirrhotic patients with AGIB was validated. Machine learning (M...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhaohui Bai, Su Lin, Mingyu Sun, Shanshan Yuan, Mariana Barros Marcondes, Dapeng Ma, Qiang Zhu, Yiling Li, Yingli He, Cyriac Abby Philips, Xiaofeng Liu, Kanokwan Pinyopornpanish, Lichun Shao, Nahum Méndez-Sánchez, Metin Basaranoglu, Yunhai Wu, Yu Chen, Ling Yang, Andrea Mancuso, Frank Tacke, Bimin Li, Lei Liu, Fanpu Ji, Xingshun Qi
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:npj Digital Medicine
Online Access:https://doi.org/10.1038/s41746-025-01883-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849341557404073984
author Zhaohui Bai
Su Lin
Mingyu Sun
Shanshan Yuan
Mariana Barros Marcondes
Dapeng Ma
Qiang Zhu
Yiling Li
Yingli He
Cyriac Abby Philips
Xiaofeng Liu
Kanokwan Pinyopornpanish
Lichun Shao
Nahum Méndez-Sánchez
Metin Basaranoglu
Yunhai Wu
Yu Chen
Ling Yang
Andrea Mancuso
Frank Tacke
Bimin Li
Lei Liu
Fanpu Ji
Xingshun Qi
author_facet Zhaohui Bai
Su Lin
Mingyu Sun
Shanshan Yuan
Mariana Barros Marcondes
Dapeng Ma
Qiang Zhu
Yiling Li
Yingli He
Cyriac Abby Philips
Xiaofeng Liu
Kanokwan Pinyopornpanish
Lichun Shao
Nahum Méndez-Sánchez
Metin Basaranoglu
Yunhai Wu
Yu Chen
Ling Yang
Andrea Mancuso
Frank Tacke
Bimin Li
Lei Liu
Fanpu Ji
Xingshun Qi
author_sort Zhaohui Bai
collection DOAJ
description Abstract Acute gastrointestinal bleeding (AGIB) is a potentially lethal complication in cirrhosis. In this prospective international multi-center study, the performance of CAGIB score for predicting the risk of in-hospital death in 2467 cirrhotic patients with AGIB was validated. Machine learning (ML) models were established based on CAGIB components, and their area under curves (AUCs) were calculated and compared. Gray zone approach was employed to further stratify the risk of death. In training cohort, the AUC of CAGIB score was 0.789. Among the ML models, the least square support vector machine regression (LS-SVMR) model had the best predictive performance (AUC = 0.986). Patients were further divided into low- (LS-SVMR score <0.084), moderate- (LS-SVMR score 0.084–0.160), and high-risk (LS-SVMR score >0.160) groups with in-hospital mortality of 0.38%, 2.22%, and 64.37%, respectively. Statistical results were retained in validation cohort. LS-SVMR model has an excellent predictive performance for in-hospital death in cirrhotic patients with AGIB (ClinicalTrials.gov; NCT04662918).
format Article
id doaj-art-edad1489273f4a4e9c6f2da52297c2c8
institution Kabale University
issn 2398-6352
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series npj Digital Medicine
spelling doaj-art-edad1489273f4a4e9c6f2da52297c2c82025-08-20T03:43:36ZengNature Portfolionpj Digital Medicine2398-63522025-07-018111210.1038/s41746-025-01883-wMachine learning based CAGIB score predicts in-hospital mortality of cirrhotic patients with acute gastrointestinal bleedingZhaohui Bai0Su Lin1Mingyu Sun2Shanshan Yuan3Mariana Barros Marcondes4Dapeng Ma5Qiang Zhu6Yiling Li7Yingli He8Cyriac Abby Philips9Xiaofeng Liu10Kanokwan Pinyopornpanish11Lichun Shao12Nahum Méndez-Sánchez13Metin Basaranoglu14Yunhai Wu15Yu Chen16Ling Yang17Andrea Mancuso18Frank Tacke19Bimin Li20Lei Liu21Fanpu Ji22Xingshun Qi23Liver Cirrhosis Study Group, Department of Gastroenterology, General Hospital of Northern Theater CommandLiver Research Center, The First Affiliated Hospital of Fujian Medical UniversityInstitute of Liver Diseases, Shuguang Hospital Affiliated to Shanghai University of Traditional Chinese MedicineDepartment of Gastroenterology, Xi’an Central HospitalSão Paulo State University (UNESP), Botucatu Medical SchoolDepartment of Critical Care Medicine, The Sixth People’s Hospital of DalianDepartment of Infectious Disease, Shandong Provincial Hospital affiliated to Shandong First Medical UniversityDepartment of Gastroenterology, The First Affiliated Hospital of China Medical UniversityDepartment of Infectious Diseases, The First Affiliated Hospital of Xi’an Jiaotong UniversityDepartment of Clinical and Translational Hepatology, The Liver Institute, Center of Excellence in GI Sciences, Rajagiri HospitalDepartment of Gastroenterology, The 960th Hospital of Chinese PLADepartment of Internal Medicine, Faculty of Medicine, Chiang Mai UniversityDepartment of Gastroenterology, Air Force Hospital of Northern Theater CommandMedica Sur Clinic & Foundation, National Autonomous University of MexicoGastroenterology and Hepatology, Bezmialem Vakif UniversityDepartment of Critical Care Medicine, The Sixth People’s Hospital of ShenyangDifficult and Complicated Liver Diseases and Artificial Liver Center, Beijing Youan Hospital, Capital Medical UniversityDivision of Gastroenterology, Union Hospital, Tongji Medical College, Huazhong University of Science and TechnologyMedicina Interna 1, Azienda di Rilievo Nazionale ad Alta Specializzazione Civico-Di Cristina-BenfratelliDepartment of Hepatology & Gastroenterology, Charité - Universitätsmedizin Berlin, Campus Virchow-Klinikum (CVK) and Campus Charité Mitte (CCM)Department of Gastroenterology, The First Affiliated Hospital of Nanchang UniversityDepartment of Infectious Diseases, Tangdu Hospital, Fourth Military Medical UniversityDepartment of Hepatology, The Second Affiliated Hospital of Xi’an Jiaotong UniversityLiver Cirrhosis Study Group, Department of Gastroenterology, General Hospital of Northern Theater CommandAbstract Acute gastrointestinal bleeding (AGIB) is a potentially lethal complication in cirrhosis. In this prospective international multi-center study, the performance of CAGIB score for predicting the risk of in-hospital death in 2467 cirrhotic patients with AGIB was validated. Machine learning (ML) models were established based on CAGIB components, and their area under curves (AUCs) were calculated and compared. Gray zone approach was employed to further stratify the risk of death. In training cohort, the AUC of CAGIB score was 0.789. Among the ML models, the least square support vector machine regression (LS-SVMR) model had the best predictive performance (AUC = 0.986). Patients were further divided into low- (LS-SVMR score <0.084), moderate- (LS-SVMR score 0.084–0.160), and high-risk (LS-SVMR score >0.160) groups with in-hospital mortality of 0.38%, 2.22%, and 64.37%, respectively. Statistical results were retained in validation cohort. LS-SVMR model has an excellent predictive performance for in-hospital death in cirrhotic patients with AGIB (ClinicalTrials.gov; NCT04662918).https://doi.org/10.1038/s41746-025-01883-w
spellingShingle Zhaohui Bai
Su Lin
Mingyu Sun
Shanshan Yuan
Mariana Barros Marcondes
Dapeng Ma
Qiang Zhu
Yiling Li
Yingli He
Cyriac Abby Philips
Xiaofeng Liu
Kanokwan Pinyopornpanish
Lichun Shao
Nahum Méndez-Sánchez
Metin Basaranoglu
Yunhai Wu
Yu Chen
Ling Yang
Andrea Mancuso
Frank Tacke
Bimin Li
Lei Liu
Fanpu Ji
Xingshun Qi
Machine learning based CAGIB score predicts in-hospital mortality of cirrhotic patients with acute gastrointestinal bleeding
npj Digital Medicine
title Machine learning based CAGIB score predicts in-hospital mortality of cirrhotic patients with acute gastrointestinal bleeding
title_full Machine learning based CAGIB score predicts in-hospital mortality of cirrhotic patients with acute gastrointestinal bleeding
title_fullStr Machine learning based CAGIB score predicts in-hospital mortality of cirrhotic patients with acute gastrointestinal bleeding
title_full_unstemmed Machine learning based CAGIB score predicts in-hospital mortality of cirrhotic patients with acute gastrointestinal bleeding
title_short Machine learning based CAGIB score predicts in-hospital mortality of cirrhotic patients with acute gastrointestinal bleeding
title_sort machine learning based cagib score predicts in hospital mortality of cirrhotic patients with acute gastrointestinal bleeding
url https://doi.org/10.1038/s41746-025-01883-w
work_keys_str_mv AT zhaohuibai machinelearningbasedcagibscorepredictsinhospitalmortalityofcirrhoticpatientswithacutegastrointestinalbleeding
AT sulin machinelearningbasedcagibscorepredictsinhospitalmortalityofcirrhoticpatientswithacutegastrointestinalbleeding
AT mingyusun machinelearningbasedcagibscorepredictsinhospitalmortalityofcirrhoticpatientswithacutegastrointestinalbleeding
AT shanshanyuan machinelearningbasedcagibscorepredictsinhospitalmortalityofcirrhoticpatientswithacutegastrointestinalbleeding
AT marianabarrosmarcondes machinelearningbasedcagibscorepredictsinhospitalmortalityofcirrhoticpatientswithacutegastrointestinalbleeding
AT dapengma machinelearningbasedcagibscorepredictsinhospitalmortalityofcirrhoticpatientswithacutegastrointestinalbleeding
AT qiangzhu machinelearningbasedcagibscorepredictsinhospitalmortalityofcirrhoticpatientswithacutegastrointestinalbleeding
AT yilingli machinelearningbasedcagibscorepredictsinhospitalmortalityofcirrhoticpatientswithacutegastrointestinalbleeding
AT yinglihe machinelearningbasedcagibscorepredictsinhospitalmortalityofcirrhoticpatientswithacutegastrointestinalbleeding
AT cyriacabbyphilips machinelearningbasedcagibscorepredictsinhospitalmortalityofcirrhoticpatientswithacutegastrointestinalbleeding
AT xiaofengliu machinelearningbasedcagibscorepredictsinhospitalmortalityofcirrhoticpatientswithacutegastrointestinalbleeding
AT kanokwanpinyopornpanish machinelearningbasedcagibscorepredictsinhospitalmortalityofcirrhoticpatientswithacutegastrointestinalbleeding
AT lichunshao machinelearningbasedcagibscorepredictsinhospitalmortalityofcirrhoticpatientswithacutegastrointestinalbleeding
AT nahummendezsanchez machinelearningbasedcagibscorepredictsinhospitalmortalityofcirrhoticpatientswithacutegastrointestinalbleeding
AT metinbasaranoglu machinelearningbasedcagibscorepredictsinhospitalmortalityofcirrhoticpatientswithacutegastrointestinalbleeding
AT yunhaiwu machinelearningbasedcagibscorepredictsinhospitalmortalityofcirrhoticpatientswithacutegastrointestinalbleeding
AT yuchen machinelearningbasedcagibscorepredictsinhospitalmortalityofcirrhoticpatientswithacutegastrointestinalbleeding
AT lingyang machinelearningbasedcagibscorepredictsinhospitalmortalityofcirrhoticpatientswithacutegastrointestinalbleeding
AT andreamancuso machinelearningbasedcagibscorepredictsinhospitalmortalityofcirrhoticpatientswithacutegastrointestinalbleeding
AT franktacke machinelearningbasedcagibscorepredictsinhospitalmortalityofcirrhoticpatientswithacutegastrointestinalbleeding
AT biminli machinelearningbasedcagibscorepredictsinhospitalmortalityofcirrhoticpatientswithacutegastrointestinalbleeding
AT leiliu machinelearningbasedcagibscorepredictsinhospitalmortalityofcirrhoticpatientswithacutegastrointestinalbleeding
AT fanpuji machinelearningbasedcagibscorepredictsinhospitalmortalityofcirrhoticpatientswithacutegastrointestinalbleeding
AT xingshunqi machinelearningbasedcagibscorepredictsinhospitalmortalityofcirrhoticpatientswithacutegastrointestinalbleeding