Machine learning models of noninvasive tests to predict metabolic dysfunction–associated steatohepatitis and fibrosis stage
4 affiliations
- 1MASLD Research Center, Division of Gastroenterology and Hepatology, University of California at San Diego, La Jolla, California, USA
- 2Madrigal Pharmaceuticals, Inc., West Conshohocken, Pennsylvania, USA
- 3Cytel, Cambridge, Massachusetts, USA
- 4Mayo Clinic College of Medicine and Science, Phoenix, Arizona, USA
Abstract
Background
Fibrosis stage in metabolic dysfunction-associated steatohepatitis (MASH) is currently diagnosed by liver biopsy in clinical trials. Using noninvasive tests, no consensus method exists for staging fibrosis or diagnosing MASH. We aimed to develop machine learning (ML) methods to predict fibrosis stage and MASH with F2/F3 fibrosis using noninvasive biomarkers.Methods
Data from 1970 biopsy-confirmed patients screened for phase 3 resmetirom trials (MAESTRO-NASH, MAESTRO-NAFLD-1) were retrospectively analyzed. Outcomes were fibrosis stage and MASH with F2/F3 fibrosis [NAFLD Activity Score (NAS) ≥4 with moderate to advanced noncirrhotic fibrosis], modeled from 37 clinical, laboratory, and imaging predictors. Random forest models were developed, including a full model using all 37 predictors and "Lean" models using subsets of predictors routinely available in clinical practice. These models were evaluated by 4-fold cross-validation using AUC.Results
For three-class fibrosis staging (F0/F1 vs. F2/F3 vs. F4), one-versus-rest cross-validation mean AUCs were 0.76, 0.75, and 0.94 for the full model and 0.83, 0.78, and 0.89 for the best-performing Lean model. Liver stiffness measures (LSM) and MASH composite algorithms, such as the Fibrosis-4 Index (FIB-4) and FibroScan-AST, were among the most important predictors. For MASH with F2/F3 fibrosis, the full and best-performing Lean models achieved AUCs of 0.75 and 0.79, respectively. Parsimonious top-k models retaining LSM preserved much of this performance.Conclusion
ML models using routinely available noninvasive biomarkers discriminated fibrosis stage and MASH with F2/F3 fibrosis with strong performance, supporting patient selection for clinical trials or practice. Lean predictor models that incorporated LSM outperformed models limited to blood-based biomarkers or a combination of FIB-4 and LSM. These proposed ML models need additional external and prospective validation before deployment for clinical use.
Related
- A multicohort proteomics-based machine learning score (MASHPredict) for noninvasive diagnosis and long-term prognostication of metabolic dysfunction-associated steatohepatitis
- Identification of Neuroinflammation-Related Diagnostic Biomarkers in Metabolic Dysfunction-Associated Steatohepatitis: An Integrated Bioinformatics and Machine Learning Approach.
- Efficacy and safety of GLP-1 receptor agonists in patients with metabolic dysfunction-associated steatotic liver disease (MASLD) and metabolic dysfunction-associated steatohepatitis (MASH) : A systematic review and meta-analysis
- Commentary: Wogonoside alleviates metabolic dysfunction-associated steatohepatitis by modulating AMPK and xCT/GPX4 pathways to restrain lipid dysregulation and ferroptosis
- GLP-1 receptor agonists in metabolic dysfunction-associated steatohepatitis: protocol for a systematic review and meta-analysis of randomized controlled trials
BibTeX
@article{loomba2026machine,
title = {{Machine learning models of noninvasive tests to predict metabolic dysfunction–associated steatohepatitis and fibrosis stage}},
author = {Rohit Loomba and Rebecca Taub and Dominic Labriola and Jan Priel and Krishna Padmanabhan and W. Ray Kim},
journal = {Hepatology communications},
year = {2026},
month = oct,
doi = {10.1097/hc9.0000000000001064},
url = {https://europepmc.org/article/PMC/PMC13668301},
note = {CC BY},
}
RIS
TY - JOUR
TI - Machine learning models of noninvasive tests to predict metabolic dysfunction–associated steatohepatitis and fibrosis stage
AU - Rohit Loomba
AU - Rebecca Taub
AU - Dominic Labriola
AU - Jan Priel
AU - Krishna Padmanabhan
AU - W. Ray Kim
PY - 2026
DA - 2026/10/14
JO - Hepatology communications
DO - 10.1097/hc9.0000000000001064
UR - https://europepmc.org/article/PMC/PMC13668301
AB - Background Fibrosis stage in metabolic dysfunction-associated steatohepatitis (MASH) is currently diagnosed by liver biopsy in clinical trials. Using noninvasive tests, no consensus method exists for staging fibrosis or diagnosing MASH. We aimed to develop machine learning (ML) methods to predict fibrosis stage and MASH with F2/F3 fibrosis using noninvasive biomarkers.Methods Data from 1970 biopsy-confirmed patients screened for phase 3 resmetirom trials (MAESTRO-NASH, MAESTRO-NAFLD-1) were retrospectively analyzed. Outcomes were fibrosis stage and MASH with F2/F3 fibrosis [NAFLD Activity Score (NAS) ≥4 with moderate to advanced noncirrhotic fibrosis], modeled from 37 clinical, laboratory, and imaging predictors. Random forest models were developed, including a full model using all 37 predictors and "Lean" models using subsets of predictors routinely available in clinical practice. These models were evaluated by 4-fold cross-validation using AUC.Results For three-class fibrosis staging (F0/F1 vs. F2/F3 vs. F4), one-versus-rest cross-validation mean AUCs were 0.76, 0.75, and 0.94 for the full model and 0.83, 0.78, and 0.89 for the best-performing Lean model. Liver stiffness measures (LSM) and MASH composite algorithms, such as the Fibrosis-4 Index (FIB-4) and FibroScan-AST, were among the most important predictors. For MASH with F2/F3 fibrosis, the full and best-performing Lean models achieved AUCs of 0.75 and 0.79, respectively. Parsimonious top-k models retaining LSM preserved much of this performance.Conclusion ML models using routinely available noninvasive biomarkers discriminated fibrosis stage and MASH with F2/F3 fibrosis with strong performance, supporting patient selection for clinical trials or practice. Lean predictor models that incorporated LSM outperformed models limited to blood-based biomarkers or a combination of FIB-4 and LSM. These proposed ML models need additional external and prospective validation before deployment for clinical use.
SN - 2471-254X
ER -