Random Forest in Detecting Hepatitis C

Hepatitis C is a heart illness caused by the Hepatitis C Virus; if it persists for an extended period, it can lead to chronic heart disease, heart failure, and even heart cancer. In most cases, Hepatitis C is self-curable; but, in some instances, Hepatitis C can develop into a chronic illness. In such a case, the physician may prescribe an antiviral medication or, if complications arise, suggest a heart transplant. Hepatitis C Virus is transmissible by blood; this transmission can occur after a blood transfusion or when two or more persons use a syringe. Hepatitis C Virus can also be transmitted through unprotected sexual contact with an infected individual. Early methods of Hepatitis C diagnosis and classification were ineffective and inefficient. This is because the approach employed is still a conventional one involving laboratory testing, which might be time-consuming to discover. Aside from it, the majority of causes that contributed to this sickness remain unclear. For medical teams to classify the Hepatitis C virus with precision, efficiency, and speed, it is necessary to construct machine learning-based prediction models. In this study,we proposed random forest algorithm to classify Hepatitis C. We are also compared our proposed method to other algorithms such as Naive Bayes, KNN, and Decision Tree. We employed three different scenarios to proof our hypothesis regarding the importance of cross validation in dataset. The result showed always performed the best in three different scenarios with the accuracy results are 98.37%, 99.46%, 99.19%.