Optimizing hepatitis C diagnosis through reinforcement learning feature selection and multi-model machine learning
Kanica Anand Arora1, Anuj Sharma2, Deepak Prashar2,3
1School of Computer Applications, Lovely Professional University, Phagwara, Punjab, India. kanicaanand01@gmail.com.
Insights
This study introduces a novel multi-agent reinforcement learning (MARL) framework for Hepatitis C virus (HCV) diagnosis, significantly reducing complexity and cost. The system identifies key biomarkers, achieving high accuracy with fewer features.
Area of Science:
- Medical Informatics
- Artificial Intelligence in Healthcare
- Hepatology
Background:
- Hepatitis C virus (HCV) infection affects 50 million globally, leading to liver cirrhosis and cancer.
- Current diagnostic methods for HCV are complex and costly, often lacking improved accuracy.
- Optimizing diagnostic approaches is crucial for effective patient management and public health.
Purpose of the Study:
- To develop and validate a novel multi-agent reinforcement learning (MARL) framework for intelligent feature selection in HCV diagnosis.
- To identify minimal yet highly effective biomarker subsets for accurate HCV classification.
- To reduce diagnostic complexity and healthcare costs associated with traditional diagnostic methods.
Main Methods:
- A four-agent MARL system (Greedy Q-learning, Exploratory Q-Learning, Parsimonious DQN, Random) was developed for dynamic feature selection.
- The framework was validated on a real-world dataset of 1,004 patients with 14 clinical features.
- Selected features were evaluated using Logistic Regression, Decision Tree, Random Forest, and XGBoost classifiers.
Main Results:
- The MARL framework identified compact feature subsets (3-4 features) achieving high diagnostic performance (accuracy: 0.98-0.99, F1-score: 0.98-0.99).
- The Parsimonious Deep Q-Network (DQN) agent consistently outperformed other agents.
- Serum Glutamic Oxaloacetic Transaminase (SGOT) was identified as a critical biomarker for HCV detection.
Conclusions:
- Reinforcement learning-based adaptive feature selection significantly enhances HCV diagnostic efficiency.
- The MARL framework offers a scalable, interpretable, and clinically viable solution for early HCV detection.
- This approach has potential applications in various healthcare analytics domains beyond HCV diagnosis.
Abstract:
Hepatitis C virus (HCV) infection remains a leading cause of liver cirrhosis and hepatocellular carcinoma globally, affecting approximately 50 million people with chronic infection worldwide. Traditional diagnostic approaches often rely on extensive biomarker panels, resulting in increased healthcare costs and clinical complexity without corresponding improvements in diagnostic accuracy. This study presents a novel multi-agent reinforcement learning (MARL) framework for optimizing HCV diagnosis through intelligent feature selection, aiming to identify minimal yet highly effective biomarker subsets while maintaining superior classification performance. We developed a four-agent MARL system comprising Greedy Q-learning, Exploratory Q-Learning, Parsimonious Deep Q-Network (DQN), and Random agents to dynamically select optimal feature subsets from clinical data. The framework was validated using a real-world dataset of 1,004 patients with 14 clinical features from Government Medical College, Bakshi Nagar, Jammu, India. Selected features were evaluated across four machine learning classifiers: Logistic Regression, Decision Tree, Random Forest, and XGBoost. The MARL framework successfully identified compact feature subsets (3-4 features) achieving exceptional diagnostic performance (accuracy: 0.98-0.99, F1-score: 0.98-0.99). The Parsimonious DQN agent consistently outperformed other approaches across all classifiers. Notably, SGOT emerged as the most critical biomarkers for HCV detection. The framework demonstrated robust stability across six independent experimental runs, with ensemble methods (Random Forest and XGBoost) showing superior performance with RL-selected features. This study demonstrates that reinforcement learning-based adaptive feature selection significantly reduces diagnostic complexity and healthcare costs while maintaining or exceeding the performance of traditional full-feature approaches. The MARL framework offers a scalable, interpretable, and clinically viable solution for early HCV diagnosis, with potential applications across diverse healthcare analytics domains.
