ALADDIN: A Machine Learning Approach to Enhance the Prediction of Significant Fibrosis or Higher in Metabolic Dysfunction-Associated Steatotic Liver Disease

Authors

• Naim Alkhouri
• Terry Cheuk-Fung Yip
• Laurent Castera
• Marina Takawy
• Leon A Adams
• Nipun Verma
• Juan Pablo Arab
• Syed-Mohammed Jafri
• Bihui Zhong
• Julie Dubourg
• Vincent L Chen
• Ashwani K Singal
• Luis Antonio Díaz
• Nicholas Dunn
• Rida Nadeem
• Vincent Wai-Sun Wong
• Manal F Abdelmalek
• Zhengyi Wang
• Ajay Duseja
• Yousef Almahanna
• Haya A Omeish
• Junzhao Ye
• Stephen A Harrison
• Jessica Cristiu
• Marco Arrese
• Sage Robert
• Grace Lai-Hung Wong
• Amani Bajunayd
• Congxiang Shao
• Matthew Kubina
• Winston Dunn

Language

English

Publication Date

2-1-2026

Journal

American Journal of Gastroenterology

DOI

10.14309/ajg.0000000000003432

PMID

40146016

PMCID

PMC12854381

PubMedCentral® Posted Date

3-27-2025

PubMedCentral® Full Text Version

Post-print

Abstract

Introduction: The recent US Food and Drug Administration approval of resmetirom for treating metabolic dysfunction-associated steatohepatitis in patients necessitates patient selection for significant fibrosis or higher (≥F2). No existing vibration-controlled transient elastography (VCTE) algorithm targets ≥F2.

Methods: The mAchine Learning ADvanceD fibrosis and rIsk metabolic dysfunction-associated steatohepatitis Novel predictor (ALADDIN) study addressed this gap by introducing a machine-learning-based web calculator that estimates the likelihood of significant fibrosis using routine laboratory parameters with and without VCTE. Our study included a training set of 827 patients, a testing set of 504 patients with biopsy-confirmed metabolic dysfunction-associated steatotic liver disease from 6 centers, and an external validation set of 1,299 patients from 9 centers. Five algorithms were compared using area under the curve (AUC) in the test set: ElasticNet, random forest, gradient boosting machines, XGBoost, and neural networks. The top 3 (random forest, gradient boosting machines, and XGBoost) formed an ensemble model.

Results: In the external validation set, the ALADDIN-F2-VCTE model, using routine laboratory parameters with VCTE (AUC 0.791, 95% confidence interval [CI]: 0.764-0.819), outperformed VCTE alone (0.745, 95% CI 0.717-0.772, P < 0.0001), FibroScan-aspartate aminotransferase (0.710, 0.679-0.748, P < 0.0001), and Agile-3 model (0.740, 0.710-0.770, P < 0.0001) regarding the AUC, decision curve analysis, and calibration. The ALADDIN-F2-Lab model, using routine laboratory parameters without VCTE, achieved an AUC of 0.706 (95% CI: 0.668-0.749) and outperformed Fibrosis-4, steatosis-associated fibrosis estimator, and LiverRisk scores.

Discussion: Along with the steatosis-associated fibrosis estimator model developed to target significant fibrosis or higher, ALADDIN-F2-VCTE ( https://aihepatology.shinyapps.io/ALADDIN1 ) uniquely supports a refined noninvasive approach to patient selection for resmetirom without the need for liver biopsy. In addition, ALADDIN-F2-Lab ( https://aihepatology.shinyapps.io/ALADDIN2 ) offers an effective alternative when VCTE is unavailable.

Keywords

Humans, Machine Learning, Liver Cirrhosis, Male, Elasticity Imaging Techniques, Female, Middle Aged, Fatty Liver, Algorithms, Adult, Non-alcoholic Fatty Liver Disease, Predictive Value of Tests, artificial intelligence, VCTE, FibroScan, fibrosis, model, steatohepatitis, machine learning, outcome prediction

Published Open-Access

yes

Recommended Citation

Alkhouri, Naim; Cheuk-Fung Yip, Terry; Castera, Laurent; et al., "ALADDIN: A Machine Learning Approach to Enhance the Prediction of Significant Fibrosis or Higher in Metabolic Dysfunction-Associated Steatotic Liver Disease" (2026). Faculty, Staff and Students Publications. 8287.
https://digitalcommons.library.tmc.edu/baylor_docs/8287