AI based solution for Predicting Hepatitis C Virus from Blood Samples

Hepatitis - C Virus (HCV) infection stands as a prominent cause of chronic liver disease on a global scale. Predicting HCV poses a significant challenge in the medical field, as the abundance of healthcare data remains underutilized. To tackle this issue, it is imperative to collect relevant data, extract valuable insights and employ them effectively. Consequently data mining holds immense potential across various industries and scientific domains. The objective of this research work is to meticulously analyze and visualize the dataset’s variables aiming to identify essential factors related with HCV. Given the substantial prevalence of HCV, its impact on liver health and potential fatality emphasize the urgent and potential need to develop an accurate prediction models. However, the classification modelling like Support Vector Machine, Decision Tree, Logistic Regression & Random Forest were implemented with the help of feature selection and without feature selection. From the results, it is observed Random Forest with feature selection out performed with an accuracy of $89 \%$ and without feature selection with an accuracy of $88.33 \%$. These models are indispensable in contemporary society.