Identification and classification of hepatitis C virus: an advance machine-learning-based approach

Abstract

Hepatitis C virus (HCV) is identified as one of the leading sources of liver disease transmitted through blood-to-blood contact worldwide. HCV contamination is flattering a foremost universal health challenge, and due to its complications, more than 3 million new infectious patients along with 350,000 deaths are occurring every year. In the future, hepatitis C (HC) may be considered as one of the reasons for malaise and fatality of human, as it has been estimated that nearly 170 million have been infected by this. The last decades of medical research are evident that detecting and finding solutions for HC has remained a major concern in Egypt. As Egyptian blood donors were found highest among other blood donors from all nationalities, HCV became a major community health concern. To cope with such a problem, some of the statistical-based approaches are being developed and became a partial solution to some extent. To address the challenges of healthcare, a wide range of tools, techniques, and frameworks have been offered by machine learning (ML). As ML approaches have the capability of determining and recognizing patterns in complex datasets, they are identified as the best connectionist systems to predict the future outcomes of the HCV. In this chapter, we propose experimental investigations on the study of various ML approaches for the diagnosis of associated risk factors, cofactors promoting its progression, complications in the prevention and control of HCV in Egypt. Further, the project will focus on some of the basic ML strategies along with the challenges of handling the HC disease.