USING ARTIFICIAL INTELLIGENCE METHODS FOR DETECTION OF HCV-CAUSED DISEASES

Abstract

Diseases caused by the Hepatitis C Virus (HCV) can reach a chronic level and even lead to more serious diseases such as cirrhosis and fibrosis. In this respect, early detection of HCV infection is important. HCV-related diseases can usually be detected by applying the HCV test as a result of observing certain symptoms. However, In the early stages of infection, when symptoms are not yet evident, patients rarely resort to HCV testing. This shows that different materials are needed to guide HCV testing in order to detect HCV-related diseases early. Developing artificial intelligence technology can be an alternative to these materials, which are necessary for the early diagnosis of the disease. In this study, artificial intelligence technology was used to determine the disease status of individuals by using blood data. In the study in which the blood values of 615 individuals were used; preprocessing, filtering, feature selection, and classification processes were applied. Correlation method was used for feature selection. The features with high correlation values are selected and given as input to 5 different classification algorithms. According to the results of the study, the best classification success for the detection of HCV patients was obtained with the K-Nearest Neighbor (KNN) algorithm as 99.1%. Looking at the results of this classification, it is understood that thanks to the algorithm used, clear information about hepatitis infection can be obtained from different blood values.