Related Experiment Video
Updated: May 1, 2026
Prediction of HIV-1 Coreceptor Usage Tropism by Sequence Analysis using a Genotypic Approach
Published on: December 1, 2011
Machine learning-based prediction of treatment response in comorbid hepatitis C patients receiving DAA therapy: a
Dur E Nishwa1, Zeeshan Abbas2, Seung Won Lee1,3,4,5,6
1Department of Precision Medicine, Sungkyunkwan University, School of Medicine, Suwon, Republic of Korea.
Insights
Machine learning models can predict Hepatitis C virus (HCV) treatment success in Pakistan. Routine clinical data, including ALT and AST levels, are key predictors for sustained virological response (SVR) in comorbid patients.
Area of Science:
- Hepatology
- Medical Informatics
- Machine Learning in Healthcare
Background:
- Hepatitis C virus (HCV) infection is a significant public health challenge in Pakistan, particularly in patients with comorbidities.
- Direct-acting antivirals (DAAs) are available, but predictive models for treatment outcomes are lacking in resource-limited settings.
Purpose of the Study:
- To develop and evaluate machine learning (ML) models for predicting sustained virological response (SVR) in comorbid HCV patients in Pakistan.
- To identify key clinical parameters that predict treatment failure.
Main Methods:
- A retrospective cohort study of 221 comorbid HCV patients treated with Sofosbuvir + Daclatasvir ± Ribavirin.
- Data preprocessing included standard scaling and SMOTE for class imbalance.
- Five ML models (Logistic Regression, Decision Tree, Random Forest, XGBoost, SVM) were trained and evaluated using stratified cross-validation and performance metrics (accuracy, precision, recall, F1-score, ROC-AUC).
- SHAP analysis was performed on the best-performing model.
Main Results:
- 162 out of 221 patients (73%) achieved SVR.
- Random Forest and Support Vector Machine (SVM) showed the best performance.
- Random Forest achieved the highest accuracy (0.73), precision (0.84), and F1-score (0.81).
- SVM yielded the highest recall (0.82) and ROC-AUC (0.76).
- Alanine aminotransferase (ALT) and aspartate aminotransferase (AST) were the strongest predictors of treatment failure.
Conclusions:
- ML models utilizing routine clinical data can effectively predict SVR in HCV patients in resource-limited settings.
- These tools can aid in risk stratification, monitoring optimization, and public health strategies for HCV elimination.
- Further validation in larger, multicenter cohorts is recommended.
Introduction:
Hepatitis C virus (HCV) infection remains highly prevalent in Pakistan, particularly among patients with multiple comorbid conditions. Despite the widespread availability of direct-acting antivirals (DAAs), practical machine learning approaches to predict sustained virological response (SVR) are still lacking in resource-limited settings.
Methods:
This retrospective cohort study analyzed 221 comorbid HCV patients treated with Sofosbuvir + Daclatasvir ± Ribavirin combination therapy. Baseline demographic and laboratory parameters were preprocessed using standard scaling methods. The dataset was split into 70% training and 30% testing subsets, and class imbalance in the training set was addressed using SMOTE. Five machine learning models, logistic regression, decision tree, random forest, XGBoost, and SVM, were tuned using stratified five-fold cross-validation. Evaluation metrics, including accuracy, precision, recall, specificity, F1-score, and ROC-AUC, were used to assess test-set performance, and SHAP analysis was conducted for the top-performing model.
Results:
Among the 221 patients, 162 (73%) achieved SVR. Random Forest and SVM demonstrated the best discriminatory performance, with Random Forest achieving the highest accuracy (0.73), precision (0.84), and F1-score (0.81), while SVM produced the highest recall (0.82) and ROC-AUC (0.76). ALT and AST consistently emerged as the strongest predictors associated with treatment failure.
Conclusion:
These findings support the potential of ML-based decision tools using routine clinical data in high-burden, resource-limited settings to guide risk stratification, optimize monitoring intensity, and inform public health strategies for HCV control and elimination in Pakistan and highlight the need for broader validation across larger, multicenter cohorts.
More Related Videos
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
12:24A Three-Dimensional Spheroid Model to Investigate the Tumor-Stromal Interaction in Hepatocellular Carcinoma
Published on: September 30, 2021
Related Concept Videos
01:29Therapeutic Drug Monitoring: Affecting Factors
01:26Effect of Hepatic Disease on Pharmacokinetics: Drug Dosing and Hepatic Blood Flow
01:22Effect of Hepatic Disease on Pharmacokinetics: Pathophysiologic Assessment and Liver Function Test
01:08Effect of Hepatic Disease on Pharmacokinetics: Dose Adjustments Due to Hepatic Impairment
01:24Pharmacokinetic–Pharmacodynamic Relationship: Problems