Machine Learning for Predicting Hepatitis C Virus Therapy Outcomes

Although the current scientific revolution and the great improving of the health care systems, hepatitis C virus (HCV) continues to be a major health risk in both developed and developing countries and is considered one of the most important causes of chronic liver disease. It accounts for about 15% of acute viral hepatitis, 60% to 70% of chronic hepatitis C(CHC) and up to 50% of cirrhosis, end-stage liver disease and liver cancer. An estimated 150-200 million people worldwide are infected with hepatitis C. Unfortunately,there are a few published simulation models related to HCV problem.All attempts depending on one mathematical model that describes the virologic infections published by Alan Perelson at 1999. After that, many researchers applied this model on studying hepatitis C dynamics. Comparatively higher rate of sustained virologic response(SVR)which defined as undetectable HCV ribonucleic acid(RNA)and end of treatment response(ETR) observed more pronounced in patients treated with pegylated interferon (Peg-IFN) and ribavirin(RBV) than standard combination treatment. Patients with CHC often stop subsuming the treatment because of the high cost and related unfavorable effects.