Hepatitis C Disease Detection Based on PCA–SVM Model

Hepatitis C is a liver disease caused by infection with the hepatitis virus (HCV), which transmitted through blood. The can lead to diseases ranging from mild form serious lifelong illness. Studies detect early and reduce its effect are continuing. This study proposes an effective support vector machine model supported principal component analysis for detecting c disease. dataset consisted of twelve independent variables, each containing 582 samples, these variables were used as inputs two classifiers, (SVM) artificial neural network (ANN). accuracy, sensitivity, specificity, MCC KAPPA calculated using classification models. In addition, performance comparisons classifiers made cases without PCA (principal analysis) applied inputs. highest accuracy (98.7%), sensitivity (99.1%), specificity (95.2%), (92.3%) Kappa in binary class label obtained SVM PCA. four-class label, was achieved same 95.7%. results show that classifier model, PCA-reduced inputs, may be candidate accurate prediction predict