Application of Interpretable Machine Learning Models to Predict the Risk Factors of HBV-Related Liver Cirrhosis in...

Area of Science:

• Hepatology and Artificial Intelligence
• Clinical Informatics
• Predictive Modeling in Medicine

Background:

• Chronic hepatitis B (CHB) is a major global health concern, frequently progressing to hepatitis B virus-related liver cirrhosis (HBV-LC).
• Early identification of HBV-LC risk is crucial for timely and effective patient management.
• Existing prediction methods may lack accuracy or accessibility in resource-limited settings.

Purpose of the Study:

• To develop and compare nine machine learning (ML) models for predicting HBV-LC risk in CHB patients.
• To identify key clinical and laboratory variables predictive of HBV-LC development.
• To create an interpretable and accurate ML tool for early HBV-LC risk assessment.

Main Methods:

• Retrospective analysis of 777 CHB patients, with 50.45% progressing to HBV-LC.
• Utilized 52 clinical/laboratory variables, employing multiple imputation for missing data.
• Applied LASSO regression and Boruta algorithm for feature selection, identifying 24 key predictors.
• Evaluated nine ML models including Random Forest (RF), XGBoost, and Logistic Regression (LR).
• Assessed model performance using AUC, Brier score, accuracy, sensitivity, specificity, and F1 score, with cross-validation for tuning.

Main Results:

• The Random Forest (RF) model achieved superior performance with an AUC of 0.992 (training) and 0.907 (validation).
• A reconstructed model based on RF demonstrated strong predictive power with an AUC of 0.863 on the independent testing set.
• SHAP analysis identified RPR, PLT, HBV DNA, ALT, and TBA as critical predictors for HBV-LC.
• Calibration curves and decision curve analysis confirmed the RF model's accuracy and clinical utility.

Conclusions:

• An interpretable machine learning model, particularly Random Forest, can effectively predict HBV-LC risk in CHB patients using routine clinical data.
• The developed model enhances early risk identification, supporting clinical decision-making, especially in resource-limited environments.
• Key predictors like RPR, PLT, HBV DNA, ALT, and TBA offer valuable insights into HBV-LC pathogenesis and progression.