Machine Learning–Based Biomarker Identification for Early Diagnosis of Metabolic Dysfunction–Associated Steatotic Liver Disease - Summary - MDSpire

Machine Learning–Based Biomarker Identification for Early Diagnosis of Metabolic Dysfunction–Associated Steatotic Liver Disease

  • By

  • Jolie Boullion

  • Amanda Husein

  • Akshat Agrawal

  • Diensn Xing

  • Md Ismail Hossain

  • Md Shenuarin Bhuiyan

  • Oren Rom

  • Steven A Conrad

  • John A Vanchiere

  • A Wayne Orr

  • Christopher G Kevil

  • Mohammad Alfrad Nobel Bhuiyan

  • February 21, 2025

  • 0 min

Share

Objective:

To investigate the association between biomarkers and hepatic steatosis and stiffness measurements to aid in the early diagnosis of MASLD, which includes both simple hepatic steatosis and steatohepatitis.

Key Findings:
  • Random Forest models predicted MASLD with 79.59% accuracy and specificity of 84.65%, indicating a strong predictive capability.
  • Hepatic fibrosis was predicted with 86.07% accuracy and sensitivity of 98.01%, highlighting the model's effectiveness.
  • Significant biomarkers included age, BMI, and insulin for both steatosis and stiffness.
Interpretation:

Assessing a variety of biomarkers may provide valuable insights for diagnosing MASLD and hepatic fibrosis, potentially reducing reliance on invasive liver biopsies and improving clinical outcomes.

Limitations:
  • Study limited to data from NHANES, which may not represent all populations.
  • Potential biases in self-reported data, particularly regarding health status and lifestyle factors, and exclusion of certain patient groups.
Conclusion:

The study highlights the potential of machine learning in identifying biomarkers for early detection of MASLD, which could improve clinical outcomes.

Original Source(s)

Machine Learning–Based Biomarker Identification for Early Diagnosis of Metabolic Dysfunction–Associated Steatotic Liver Disease

  • by Jolie Boullion, Amanda Husein, Akshat Agrawal, Diensn Xing, Md Ismail Hossain, Md Shenuarin Bhuiyan, Oren Rom, Steven A Conrad, John A Vanchiere, A Wayne Orr, Christopher G Kevil, Mohammad Alfrad Nobel Bhuiyan

  • February 21, 2025

Related Content

Prediction of Metabolic Dysfunction–Associated Steatotic Liver Disease via Advanced Machine Learning Among Chinese Han Population

Impact of Chlorella vulgaris Supplementation on Health Outcomes in Individuals with Non-Alcoholic Fatty Liver Disease: A Systematic Review and Meta-Analysis Evaluated by GRADE

NPs Top US Jobs List Again

The nurse practitioner profession claims the No. 1 spot across three categories in the U.S. News & World Report 2026 Best Jobs rankings for the third consecutive year.