Prediction of hepatitis prognosis using Support Vector Machines and Wrapper Method

Abstract

Hepatitis patients are those who need continuous special medical treatment to reduce mortality rate. Using clinical test findings data and machine learning technology such as Support Vector Machines (SVM), the classification and prediction of their life prognosis can be done. However, we cannot pledge that all the features values in the data are correlated to each other. Therefore, we incorporate Wrapper Methods to remove noise features before classification. This study shows the increase in prediction between data by combining feature selection method prior to classification process.