Performance Comparison of Machine Learning Approaches on Hepatitis C Prediction Employing Data Mining Techniques

Area of Science:

• Hepatology
• Medical Informatics
• Machine Learning in Healthcare

Background:

• Hepatitis C virus (HCV) infection is a significant cause of liver disease.
• Late symptom onset complicates early diagnosis and treatment of Hepatitis C.
• Early detection is crucial to prevent irreversible liver damage.

Purpose of the Study:

• To develop and evaluate machine learning models for early Hepatitis C prediction.
• To utilize common and affordable blood test data for disease prediction.
• To identify the most effective machine learning algorithm for Hepatitis C diagnosis.

Main Methods:

• Six machine learning algorithms were employed: Support Vector Machine (SVM), K-nearest Neighbors (KNN), Logistic Regression, Decision Tree, Extreme Gradient Boosting (XGBoost), and Artificial Neural Networks (ANN).
• Two datasets (NHANES and UCI) were used for model training and validation.
• Model performance was assessed using metrics including accuracy, AUC, precision, recall, F1 score, and ROC analysis.

Main Results:

• Support Vector Machine (SVM) and XGBoost demonstrated the highest predictive performance.
• Both SVM and XGBoost achieved accuracy and Area Under the Curve (AUC) values exceeding 80%.
• These models proved effective in predicting Hepatitis C using standard blood test results.

Conclusions:

• Machine learning, particularly SVM and XGBoost, offers a viable approach for early Hepatitis C prediction.
• Routine blood tests combined with advanced algorithms can support medical professionals in timely diagnosis.
• This predictive capability can lead to earlier treatment and improved patient outcomes.