KLASIFIKASI PENYAKIT SIROSIS HATI DENGAN CART

The nonparametric exploratory is a method that can be used to see the relationship between the dependent variable and the independent variable. One of the types of nonparametric exploratory methods is the CART. CART is a method that presents large amounts of data to be processed in the form of a decision tree so that it becomes valuable and easy to understand information. This research aims to build a decision tree model based on medical records from patients with liver cirrhosis using the CART. This research also used 16 independent variables of 276 data that will be used as research objects. The results of this study obtained a decision tree model with an independent variable. The first used as the root node is hepatomegaly because the hepatomegaly variable has a more homogeneous value compared to the other independent variables and that there were eight groups in this research. However, due to the nature of the CART method which is unstable and very sensitive to new data, and highly dependent on the number of samples, the accuracy rate in this study is less than 70%, this is because the data in one group is unbalanced if compared to data in the other group.