Prediction of liver fibrosis stages by machine learning model: A decision tree approach

Abstract

Using Information systems and strategic tools for medical domains is constantly growing. Automated medical models play an important role in medical decision-making, helping physicians to provide a fast and accurate diagnosis or even prediction. Making use of the knowledge or even in the early stages of knowledge acquisition, different statistical mining and machine learning tools can be used. For instance predicting whether the patient with Hepatitis C virus has also liver fibrosis or not is one of the concerns. In case the prediction result is true, in what stage is the fibrosis. To easily reach to this knowledge without costly diagnostic routine laboratory tests there should be a fully integrated system. Therefore in this study we used machine learning technique model based on decision tree classifier to predict individuals' liver fibrosis degree. Results showed that by using decision tree classifier accuracy is 93.7% which is higher range than what is reported in current researches with similar conditions.

Ähnliche Arbeiten