Machine Learning-Based Biomarker Identification for Early Diagnosis of Metabolic Dysfunction-Associated Steatotic Liver Disease
- PMID: 39980343
- PMCID: PMC12278777
- DOI: 10.1210/clinem/dgaf111
Machine Learning-Based Biomarker Identification for Early Diagnosis of Metabolic Dysfunction-Associated Steatotic Liver Disease
Abstract
Context: Metabolic dysfunction-associated steatotic liver disease (MASLD) is an umbrella term for simple hepatic steatosis and the more severe metabolic dysfunction-associated steatohepatitis. The current reliance on liver biopsy for diagnosis and a lack of validated biomarkers are major factors contributing to the overall burden of MASLD.
Objective: This study investigates the association between biomarkers and hepatic steatosis and stiffness measurements, measured by FibroScan®.
Methods: Data from the National Health and Nutritional Examination Survey (2017-2020) were collected for 15 560 patients. Propensity score matching balanced the data with a 1:1 case to control for age and sex allowing for preliminary trend assessment. Random Forest machine learning determined variable importance for the incorporation of key biomarkers (age, sex, race, BMI, HbA1c, plasma fasting glucose, insulin, total cholesterol, LDL-cholesterol, HDL-cholesterol, triglycerides, ALT, AST, ALP, albumin, GGT, LDH, iron, total bilirubin, total protein, uric acid, BUN, and hs-CRP) into logistic regression models predicting steatosis (MASLD indicated by a controlled attenuation parameter score of ≥238 dB/m) and stiffness (hepatic fibrosis indicated by a median liver stiffness ≥7 kPa). Sensitivity analysis using XGBoost and Recursive Feature Elimination was performed.
Results: The Random Forest models (the most accurate) predicted MASLD with 79.59% accuracy (P < .001) and specificity of 84.65% and predicted hepatic fibrosis with 86.07% accuracy (P < .001) and sensitivity of 98.01%. Both the steatosis and stiffness models identified statistically significant biomarkers, with age, BMI, and insulin appearing significant to both.
Conclusion: These findings indicate that assessing a variety of biomarkers, across demographic, metabolic, lipid, and standard biochemistry categories, may provide valuable initial insights for diagnosing patients for MASLD and hepatic fibrosis.
Keywords: MASLD; biomarker; hepatic fibrosis.
© The Author(s) 2025. Published by Oxford University Press on behalf of the Endocrine Society. All rights reserved. For commercial re-use, please contact reprints@oup.com for reprints and translation rights for reprints. All other permissions can be obtained through our RightsLink service via the Permissions link on the article page on our site—for further information please contact journals.permissions@oup.com. See the journal About page for additional terms.
Figures
Comment in
-
Noninvasive Tests Developed Using Artificial Intelligence for Screening in MASLD: Interest and Pitfalls.J Clin Endocrinol Metab. 2026 Feb 20;111(3):e959-e960. doi: 10.1210/clinem/dgaf294. J Clin Endocrinol Metab. 2026. PMID: 40388374 No abstract available.
References
-
- Powell EE, Wong VW, Rinella M. Non-alcoholic fatty liver disease. Lancet. 2021;397(10290):2212‐2224. - PubMed
-
- Younossi Z, Anstee QM, Marietti M, et al. Global burden of NAFLD and NASH: trends, predictions, risk factors and prevention. Nat Rev Gastroenterol Hepatol. 2018;15(1):11‐20. - PubMed
-
- Nonalcoholic Fatty liver Disease (NAFLD) . American Liver Foundation. Updated October 24, 2024. Accessed October 30, 2024. https://liverfoundation.org/liver-diseases/fatty-liver-disease/nonalcoho...
MeSH terms
Substances
Grants and funding
- R00 HL150233/HL/NHLBI NIH HHS/United States
- R01 DK134011/DK/NIDDK NIH HHS/United States
- R01 HL141155/HL/NHLBI NIH HHS/United States
- R01 HL133497/HL/NHLBI NIH HHS/United States
- R01 DK136685/DK/NIDDK NIH HHS/United States
- R01 HL149264/HL/NHLBI NIH HHS/United States
- R01 HL145753/HL/NHLBI NIH HHS/United States
- R01 HL172970/HL/NHLBI NIH HHS/United States
- P20 GM121307/GM/NIGMS NIH HHS/United States
- R01 HL098435/HL/NHLBI NIH HHS/United States
- R01 HL173972/HL/NHLBI NIH HHS/United States
- P20GM121307/National Institute of General Medical Sciences NIH
- P20GM121307/National Institute of General Medical Sciences NIH
- R01HL149264/National Institute of General Medical Sciences NIH
- R01HL098435/National Institute of General Medical Sciences NIH
- R01HL133497/National Institute of General Medical Sciences NIH
- HL141155/National Institute of General Medical Sciences NIH
- R01HL172970/NH/NIH HHS/United States
- R01HL145753/NH/NIH HHS/United States
- R01HL145753-01S1/NH/NIH HHS/United States
- R01HL145753-03S1/NH/NIH HHS/United States
- R01DK136685/NH/NIH HHS/United States
- R01DK134011/NH/NIH HHS/United States
- R00HL150233/NH/NIH HHS/United States
- MD Endowed Chair in Healthcare Informatics of LSU Health Sciences Center Shreveport
LinkOut - more resources
Full Text Sources
Medical
Research Materials
Miscellaneous
