Machine Learning for Hepatitis C Diagnosis: Predictive Modeling and Analysis of Clinical Biomarkers
Abstract
Hepatitis C, a liver disease caused by the Hepatitis C virus (HCV), affects millions globally, often progressing asymptomatically until severe liver damage occurs. This study utilizes machine learning algorithms to classify patients based on various clinical and biochemical parameters available in the Hepatitis C dataset. We apply Decision Trees, Logistic Regression, and Random Forest classifiers to predict the liver condition category of patients. Our Random Forest model achieves an accuracy of 93%, revealing the strong potential of supervised learning in early and efficient hepatitis diagnosis.
Keywords
Download Options
Introduction
Hepatitis C (HCV) is a bloodborne virus that causes liver inflammation and potentially severe liver damage. It affects an estimated 58 million people globally, with approximately 1.5 million new infections occurring annually. Early diagnosis remains a significant challenge due to its asymptomatic nature during the early stages. With advancements in data-driven healthcare, machine learning offers new ways to leverage existing clinical data to predict liver disease states more accurately.
This study explores how machine learning models can utilize the Hepatitis C dataset to predict patient status effectively, supporting early intervention and better healthcare outcomes.
Conclusion
The study demonstrates the effectiveness of Random Forest in diagnosing hepatitis conditions using clinical biomarkers. With an accuracy above 90%, such models offer scalable, non-invasive decision support tools that can assist healthcare professionals, especially in resource-limi