Abstract :

Hepatitis C Virus (HCV) is a serious infectious disease that affects millions of people globally, leading to severe liver complications such as cirrhosis and liver cancer. Early detection and accurate prediction play a crucial role in reducing mortality and improving patient survival rates. Traditional diagnostic techniques are time-consuming, costly, and sometimes unable to identify hidden disease patterns. Machine learning provides intelligent analytical capability to process medical datasets and learn significant diagnostic features. This study presents an efficient HCV prediction framework using supervised machine learning algorithms such as Random Forest, SVM, and Logistic Regression. The model focuses on clinical parameters to predict infection probability with high accuracy. The experimental results demonstrate improved diagnostic reliability compared to existing manual systems.