Hepatitis C is an infectious disease caused by the hepatitis C virus and it primarily affects the liver. Hepatitis C often leads to liver disease and occasionally cirrhosis while in some cases, those with cirrhosis will develop complications such as liver failure. This study was aimed at developing a classification model for the classification of the survival of patients living with hepatitis C. The study collected data containing 19 attributes and 155 records from an online repository created by UCI machine learning repository following which C4.5 decision trees algorithm was adopted for developing the classification model. The results of the study showed that the decision tree is suitable for developing the classification model because of its structural representation of the classification of the survival of Hepatitis C disease. The evaluation of the model simulation process showed that the best performance using the percentage split was achieved using 90 percent for training and 10 percent for testing with an accuracy of 86.67% while using the k-fold cross validation was achieved using 10-fold with an accuracy of 83.87%. Overall, the best performance was achieved using 90 percent of the dataset for training and 10 percent for testing owing for an accuracy of 86.67%. The results also showed that a number of variables were extracted from the initially identified variables and were deemed more relevant for the classification of survival. The study concluded that the If-Then rules which were extracted from the decision tree proved effective in providing decision-support to experts due to its simplicity in interpretation thus mitigating deaths associated with hepatitis C disease.
