.png){kind=icon}
.png){kind=icon}
Return
A machine learning approach to non-invasive prediction of hepatic decompensation in compensated advanced chronic liver disease: the CIRI model
.png){kind=icon}
OA
AI
G
A
C
R
V
H
K
N
C
B
B
M
T
J
P
DOI：10.1016/j.jhep.2026.06.042.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• The CIRI (Cirrhosis Risk Identifier) machine-learning model based on routine data predicts first decompensation in cACLD • CIRI was validated in large U.S. and European cACLD cohorts • Prognostic performance matched HVPG and exceeded LSM and FIB-4 • Distinct CIRI thresholds identified graded decompensation-risk groups • Scalable risk stratification by the CIRI model may help guide preventive strategies in cACLD
Keywords:
Cirrhosis
clinically significant portal hypertension
non-invasive tests
machine learning
liver stiffness
ACLD / cACLD
(compensated) advanced chronic liver disease
AFT
accelerated failure time
ALD
alcohol-related liver disease
ALT
alanine aminotransferase
AST
aspartate aminotransferase
AUC
area under the curve
AUROC
area under the receiver operating characteristic curve
aSHR / SHR
(adjusted) subdistribution hazard ratio
CDM
Clinformatics Data Mart
CI
confidence interval
CIRI
Cirrhosis Risk Identifier
CSPH
clinically significant portal hypertension
CVRM
cardiovascular, renal and metabolism
dACLD
decompensated advanced chronic liver disease
FIB-4
fibrosis-4 index
HBV
hepatitis B virus
HCC
hepatocellular carcinoma
HCV
hepatitis C virus
HVPG
hepatic venous pressure gradient
ICD
International Classification of Diseases
INR
international normalized ratio
IQR
interquartile range
LOINC
Logical Observation Identifiers Names and Codes
LRE
liver-related event
LSM
liver stiffness measurement
MASLD
metabolic dysfunction-associated steatotic liver disease
MELD
Model for End-Stage Liver Disease
MetALD
metabolic and alcohol-related liver disease
ML
machine learning
NA
not available / not applicable
NASH
non-alcoholic steatohepatitis
NDC
National Drug Code
NIT(s)
non-invasive test(s)
NPV
negative predictive value
NSBB(s)
non-selective beta-blocker(s)
PH
portal hypertension
PPV
positive predictive value
PVT
portal vein thrombosis
SD
standard deviation
SHAP
Shapley additive explanations
SLD
steatotic liver disease
SSM
spleen stiffness measurement
SVR
sustained virologic response
U.S.
United States
VCTE
vibration-controlled transient elastography
VCTE-LSM
vibration-controlled transient elastography liver stiffness measurement
VICIS
Vienna Cirrhosis Study
VIF
variance inflation factor
VITRO
von Willebrand factor antigen to platelet ratio
vWF / vWFAg
von Willebrand factor / von Willebrand factor antigen
XGBoost
Extreme Gradient Boosting
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
33
Papers:
3.2W
Citations:
6.5W
Organization
Cited Papers