Related Experiment Videos
Cross-Model Explainability Consistency in Hepatitis C Stage Classification: A SHAP, LIME, and Counterfactual Analysis
1College of Computer Science and Engineering (CCSE), Taibah University, Medina 42353, Saudi Arabia.
Insights
Machine learning models can stage Hepatitis C virus (HCV) progression. The study found Cholinesterase (CHE) is a key marker for Cirrhosis, consistent across multiple models and explanation techniques.
Area of Science:
- Hepatology and Machine Learning
- Biochemical marker identification for liver disease staging
Background:
- Hepatitis C virus (HCV) affects 50 million globally, progressing through silent hepatic stages.
- Existing machine learning staging methods lack clinician-facing explanations and cross-architecture validation.
- Need for interpretable AI in understanding complex disease progression.
Purpose of the Study:
- To develop and evaluate machine learning models for staging Hepatitis C virus (HCV) infection.
- To identify and validate stage-specific biochemical markers using explainable AI techniques.
- To assess the consistency of feature importance across different model architectures.
Main Methods:
- Trained five models (Logistic Regression, Random Forest, XGBoost, LightGBM, SVM) on the UCI HCV dataset.
- Applied explainable AI methods: SHAP, LIME, and DiCE counterfactuals for feature interpretation.
- Utilized leakage-controlled pipelines, five-fold cross-validation, and cross-model Spearman agreement analysis.
Main Results:
- Boosted-tree models (XGBoost, LightGBM) showed robust performance in cross-validation (macro-F1 ~0.65).
- SHAP consistently identified AST, GGT, CHE, and ALP as important features across tree-based models.
- Cholinesterase (CHE) emerged as a leading Cirrhosis marker, with high consistency between SHAP and LIME explanations.
Conclusions:
- The developed framework successfully identifies stage-specific biochemical patterns in HCV progression.
- Convergent evidence supports Cholinesterase (CHE) as a potential marker for advanced HCV-related Cirrhosis.
- Cross-model validation of AI explanations enhances confidence in identified disease markers.
Abstract:
Background: Hepatitis C virus (HCV) affects approximately 50 million people worldwide and progresses silently through distinct hepatic stages, yet most machine learning staging approaches offer no clinician-facing explanation and rarely evaluate whether explanations hold across architectures. Methods: We trained five models-Logistic Regression, Random Forest, XGBoost, LightGBM, and SVM-on the UCI HCV dataset (615 patients, four classes after merging the seven-instance suspect blood-donor group into a single Donor/Control class) and applied SHAP, LIME, and DiCE counterfactuals. A cross-model Spearman agreement analysis quantified feature ranking consistency, with a leakage-controlled pipeline and five-fold stratified cross-validation applied. Results: In the main 5-fold cross-validation, LightGBM achieved the highest macro-F1 (0.684 ± 0.031). Under repeated-seed cross-validation, XGBoost and LightGBM gave closely matched values (0.648 ± 0.023 and 0.645 ± 0.026), indicating comparable robustness among the boosted-tree models, both marginally ahead of the remaining three, with Random Forest close behind. Logistic Regression reached the highest macro-F1 on the single held-out split (0.790), but its cross-validated score was markedly lower (0.598 ± 0.063), underlining how unstable single-split estimates are in a small, imbalanced cohort. SHAP consistently identified AST, GGT, CHE, and ALP across the tree-based models, with CHE emerging as the leading Cirrhosis-stage marker in the boosted models. Cross-model Spearman correlations reached 0.923-0.958 among tree-based models; SHAP-LIME overlap ranged from 1/5 to 4/5. Conclusions: The framework identifies stage-specific biochemical importance patterns consistent with known HCV disease progression. The convergent finding on CHE for Cirrhosis, supported by SHAP in the tree-based models and appearing among the top LIME features in three of the five model-specific Cirrhosis explanations, supports CHE as a candidate marker worth evaluating in advanced disease.