Development and Validation of a Machine Learning-based Risk Prediction Model for Liver Fibrosis in MAFLD: A Retrospective Cohort Study

Background: Metabolic dysfunction-associated fatty liver disease (MAFLD), as the most prevalent chronic liver disease globally, is closely related to the prevalence of metabolic syndrome. Liver fibrosis is a core stage in the progression of this disease, significantly increasing the risk of liver cirrhosis, liver failure, and hepatocellular carcinoma. Early identification of high-risk patients is crucial for blocking disease progression. This study aims to construct an interpretable machine learning model to provide individualized predictions of liver fibrosis risk for MAFLD patients. Method : This study selected 2,729 research subjects from January 2020 to October 2025. Through the least absolute shrinkage and selection operator (LASSO) regression, Boruta algorithm, and recursive feature elimination (RFE), eight key variables, namely ALT, AST, SBP, BMI, WHR, DBP, LDL-C, and GGT, were selected. Predictive models employed logistic regression, decision trees, random forests, XGBoost, LightGBM, support vector machines (SVM), and artificial neural networks (ANN). Nomogram and SHapley additive predictions (SHAP) are used to explain the constructed model. Results: This study included 2728 patients with 1013 cases (38%) of liver fibrosis. The XGBoost model demonstrated strong predictive performance with training and validation set AUCs of 0.896 and 0.841, respectively, showing superior clinical accuracy among the models analyzed. Conclusion: The machine learning-based MAFLD liver fibrosis risk prediction model developed in this study demonstrated robust predictive performance and discriminative ability. It provides a reliable tool for personalized risk management in MAFLD patients and advances precision medicine approaches for this condition.