Liver Fat Fraction and Machine Learning Improve Steatohepatitis Diagnosis in Liver Transplant Patients.

Journal: NMR in biomedicine
Published Date: Jul 1, 2025

Abstract

Machine learning identifies liver fat fraction (FF) measured by H MR spectroscopy, insulinemia, and elastography as robust, non-invasive biomarkers for diagnosing steatohepatitis in liver transplant patients, validated through decision tree analysis. Compared to the general population (~5.8% prevalence), MASH is significantly more common in liver transplant recipients (~30%-50%). In patients with FF > 5.3%, the positive predictive value for MASH ranged up to 97%, more than twice the value observed in the general population.

Authors

  • Milan Hajek
    MR Unit, Department of Diagnostic and Interventional Radiology, Institute for Clinical and Experimental Medicine, Prague, Czech Republic.
  • Petr Sedivy
    MR Unit, Department of Diagnostic and Interventional Radiology, Institute for Clinical and Experimental Medicine, Prague, Czech Republic.
  • Martin Burian
    MR Unit, Department of Diagnostic and Interventional Radiology, Institute for Clinical and Experimental Medicine, Prague, Czech Republic.
  • Irena Mikova
    Department of Hepatogastroenterology, Institute for Clinical and Experimental Medicine, Prague, Czech Republic.
  • Pavel Trunecka
    Department of Hepatogastroenterology, Institute for Clinical and Experimental Medicine, Prague, Czech Republic.
  • Dita Pajuelo
    MR Unit, Department of Diagnostic and Interventional Radiology, Institute for Clinical and Experimental Medicine, Prague, Czech Republic.
  • Monika Dezortova
    MR Unit, Department of Diagnostic and Interventional Radiology, Institute for Clinical and Experimental Medicine, Prague, Czech Republic.

Keywords

External Resources

Popular Topics
Recent Journals