Extreme Gradient Boosting (XGBoost) and Support Vector Machine (SVM) models for Hepatitis C Prediction

Abstract

Hepatitis C Virus (HCV) is a worldwide epidemic. The World Health Organization estimates that annually between 3 and 4 million instances of HCV are recorded. People with HCV would benefit from knowing their illness stage earlier thanks to accurate and timely prognoses. Different noninvasive blood biochemical indicators and patient clinical data have been utilized to determine the disease phase. As a substitute for the invasive and sometimes harmful liver biopsy, machine learning approaches have shown useful in diagnosing each phase of this chronic liver disease. To accurately estimate HCV using sparse weather information, this work offers two machine learning (ML) methods: The Support Vector Machine (SVM) and a simple tree-based ensemble approach called Extreme Gradient Boosting (XGBoost). The two models are applied to real-world data on HCV. The dataset contains 13 variables and 615 cases. The results showed the SVM achieved more accuracy than the XGBoost. The SVM gets 93.5% accuracy and XGBoost gets 90.23% accuracy.