| Summary: | Hepatitis is considered to be one of the most dangerous diseases, which often leads to death if not handled properly. Thus, early detection via precise diagnosis is needed in order to prevent the unfortunate event. This research aims to provide a novel hepatitis C diagnosis based on the machine learning algorithm, which is the classification tree from the decision tree learning and the distance correlation, which measures the Euclidean distance between 2 vectors. In particular, the goal is to develop a low computational cost yet precise algorithm for diagnosing the possibility of whether a person is being infected with Hepatitis C or not. Based on the experiment, the distance correlation-based classification tree algorithm outperforms the classical classification tree algorithm by around 3% while using only 7 features instead of 12 as in the classical algorithm. Furthermore, the algorithm identified albumin (ALB), Creatinine (CREA), Bilirubin (BIL), Aspartate Transaminase (AST) and Cholesterol (CHOL) as significant risk factors in determining whether someone is potentially infected with hepatitis C or not, with Creatinine is identified as the most important parameter among all 5 parameters mentioned above.
|
|---|