Using machine learning to classify liver disease

Sasank Thapa ’22 worked with Eyad Haj Said as part of the Pakula Biomedical Fellowship Summer Research program to study how data mining can improve outcomes in liver disease.

Hepatitis C Virus (HCV) is the leading cause of viral hepatitis C in the world. HCV can develop into a chronic illness in the short span of 6 months. As this disease is often asymptomatic, it is difficult to detect with routine clinical care. Data mining techniques can be applied for early detection of the disease and early therapy or treatment. We used five machine learning models (decision tree, random forest, support vector machines, K-nearest neighbors and artificial neural network) to create a diagnostic pathway for HCV by developing models that detect HCV at all stages of the disease. Our diagnostic pathway first classifies healthy people from liver patients, and then predicts the exact disease stage.

September 29, 2021

This site uses cookies to improve your experience. Read our Web Privacy Policy for more information.

Got it! ×