Related Experiment Video
Updated: Jul 30, 2025
06:09
Author Spotlight: Advancing Hepatic Fibrosis Diagnosis Using Magnetic Resonance Elastography and AI
Published on: July 21, 2023
1.3K
Magnetic resonance elastography-based prediction model for hepatic decompensation in NAFLD: A multicenter cohort
Beom Kyung Kim1,2, Jaclyn Bergstrom1, Rohan Loomba1
1NAFLD Research Center, Division of Gastroenterology, University of California at San Diego, La Jolla, California, USA.
Hepatology (Baltimore, Md.)
|May 19, 2023
Summary
A new model using Magnetic Resonance Elastography (MRE) accurately predicts hepatic decompensation in patients with non-alcoholic fatty liver disease (NAFLD). This MRE-based tool aids in risk stratification for better patient management.
Area of Science:
- Hepatology
- Medical Imaging
- Biomarkers
Background:
- Non-alcoholic fatty liver disease (NAFLD) poses a risk for hepatic decompensation.
- Magnetic Resonance Elastography (MRE) is a reliable biomarker for liver fibrosis.
- Optimal prediction models for hepatic decompensation in NAFLD patients are needed.
Purpose of the Study:
- To develop and validate a prediction model for hepatic decompensation in NAFLD patients.
- To integrate MRE with clinical factors for enhanced risk prediction.
- To assess the model's performance against existing tools like Fibrosis-4.
Main Methods:
- An international multicenter cohort study involving 1254 NAFLD participants undergoing MRE.
- Participants were randomly assigned to training (n=627) and validation (n=627) cohorts.
- A Cox-regression model incorporating MRE and clinical factors (age, albumin, AST, platelets) was constructed and validated.
Main Results:
- The MRE-based multivariable model demonstrated excellent discrimination for 3- and 5-year hepatic decompensation risk (c-statistics 0.912 and 0.891 in training; 0.871 and 0.876 in validation).
- The model showed superior diagnostic accuracy compared to Fibrosis-4 in both cohorts.
- Hepatic decompensation was defined as variceal hemorrhage, ascites, or hepatic encephalopathy.
Conclusions:
- An MRE-based prediction model provides accurate risk stratification for hepatic decompensation in NAFLD patients.
- This model can assist clinicians in managing patients at risk of liver complications.
- MRE integration offers a promising approach for predicting adverse outcomes in NAFLD.
