A Dual Dataset approach for the diagnosis of Hepatitis C Virus using Machine Learning

Abstract

Hepatitis C (HCV) is a micro-contagion that leads to liver inflammation, sometimes affecting the liver to a serious extent. In any medical therapy, proper diagnosis of treatment response is critical for decreasing the effects of the disease. It is assessed that three to four million new cases come every year for Hepatitis C, which is a public health issue that should be solved with treatment policies and recognition. The principal motive of this paper is to implement a twofold dataset approach for the finding of Hepatitis C Virus in the general population. Popular supervised learning models like Decision tree (DT), Logistic regression (LR), K-Nearest Neighbor (KNN), Extreme gradient boosting (XGB), Ada boost (AB), Gradient Boosting Machine, Gaussian Naive Bayes, Random Forest (RF), Gradient Boosting (GB), Support Vector Machine and its variations were instigated on the classification dataset, furthermore, some unsupervised learning models like K-means, Hierarchical clustering, DBMSCN, and Gaussian Mixture algorithms were applied on the HCV clustering dataset. It was concluded that Logistic Regression and K-Means were the superlative models