Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Jun 21, 2026

Optimized Analysis of In Vivo and In Vitro Hepatic Steatosis
08:58

Optimized Analysis of In Vivo and In Vitro Hepatic Steatosis

Published on: March 11, 2017

Hepatic Steatosis Severity Prediction in Nonobese Individuals: Machine Learning Model Development and Validation.

Yitong Zhu1,2,3, Yongshuai Wang1,2,3, Shenyu Zhang1,2,3

  • 1Department of Hepatobiliary Surgery, Centre for Leading Medicine and Advanced Technologies of IHM, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China, No.96 Jinzhai Road, Hefei, Anhui, 230001, China, 86 13845159888.

Journal of Medical Internet Research
|June 19, 2026
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

ABHD17C-Mediated S-Depalmitoylation of BCL6B Enhances CD24 Transcription to Resist Macrophage Phagocytosis in Pancreatic Cancer.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

Programmable Circular Single-Stranded DNA Acts as Recyclable Anti-miRNA Nucleotides to Inhibit Colorectal Cancer.

Small methods·2026
Same author

BCAT1 inhibits crotonate-related epigenetic modulation of metabolic genes in tumor-associated macrophages to counter immunosuppression.

Nature communications·2026
Same author

MAIT cell plasticity generates CD4<sup>+</sup> MAIT cells that promote HCC progression via metabolic crosstalk with tumor cells.

Cellular & molecular immunology·2026
Same author

Development and application of G4-Flame as a visual biosensor for G4-DNA.

Nucleic acids research·2026
Same author

Reply to "Checking the shape of hepatocellular carcinoma: How irregular is irregular?"

Journal of gastroenterology·2026
This summary is machine-generated.

A new machine learning model accurately predicts hepatic steatosis severity in nonobese individuals. This tool aids early risk stratification for fatty liver disease in an underrecognized population.

Area of Science:

  • Hepatology
  • Machine Learning
  • Medical Informatics

Background:

  • Nonobese individuals experience steatotic liver disease (fatty liver disease) in 40% of cases.
  • Conventional screening tools lack sensitivity for detecting and staging fatty liver disease in nonobese populations.
  • There is a need for dedicated prediction models for this demographic.

Purpose of the Study:

  • To develop and validate an interpretable machine learning model for multiclass hepatic steatosis severity prediction.
  • To enable early risk stratification for fatty liver disease in nonobese individuals.

Main Methods:

  • Utilized health examination data from 215,145 nonobese participants.
  • Trained six machine learning algorithms, including Extreme Gradient Boosting (XGBoost), optimizing for Area Under the Receiver Operating Characteristic Curve (ROC-AUC).
Keywords:
controlled attenuation parameterhepatic steatosismachine learningnonobese populationrisk stratificationsteatotic liver disease

More Related Videos

Inducing and Characterizing Vesicular Steatosis in Differentiated HepaRG Cells
09:15

Inducing and Characterizing Vesicular Steatosis in Differentiated HepaRG Cells

Published on: July 18, 2019

Mouse Model of Metabolic Dysfunction-Associated Steatotic Liver Disease with Fibrosis
06:26

Mouse Model of Metabolic Dysfunction-Associated Steatotic Liver Disease with Fibrosis

Published on: July 18, 2025

Related Experiment Videos

Last Updated: Jun 21, 2026

Optimized Analysis of In Vivo and In Vitro Hepatic Steatosis
08:58

Optimized Analysis of In Vivo and In Vitro Hepatic Steatosis

Published on: March 11, 2017

Inducing and Characterizing Vesicular Steatosis in Differentiated HepaRG Cells
09:15

Inducing and Characterizing Vesicular Steatosis in Differentiated HepaRG Cells

Published on: July 18, 2019

Mouse Model of Metabolic Dysfunction-Associated Steatotic Liver Disease with Fibrosis
06:26

Mouse Model of Metabolic Dysfunction-Associated Steatotic Liver Disease with Fibrosis

Published on: July 18, 2025

  • Assessed model interpretability using Shapley Additive Explanations and validated externally.

    • Main Results:

    • The XGBoost model achieved high accuracy (0.824) and macro-average ROC-AUC (0.941) on the test set.
    • The model demonstrated strong external validation performance (macro-average ROC-AUC=0.874).
    • Key predictors included BMI, waist circumference, liver enzymes, renal function, and metabolic indices.

    Conclusions:

    • An interpretable XGBoost model accurately predicts hepatic steatosis severity in nonobese individuals.
    • The model shows robust performance in internal and external validation.
    • This provides a practical tool for early risk stratification in an underrecognized population.