Detecting Severity of Liver Fibrosis Classifier Using Machine Learning Assessment

Abstract

In terms of the associated risks of biopsy, noninvasive evaluation of the seriousness of liver fibrosis is important for recognizing histology & providing antiviral treatment assessments for persistent HBV. We have liver infection prediction to solve this problem. Liver disorder may be differentiated by countless systemic nature, and we have identified a multitude of classifier combinations as using estimation. For liver disease study, we used five different types of classifiers, including Nave Bayes, logistic regression, support vector machines, Random Forest, and K-Nearest Neighbor. on behalf of the classification exhibits, five unique execution metrics are measured: accuracy, mean absolute error (MAE), root-mean-square error (RMSE), and F metrics.  The purpose of this work is to use the most powerful algorithm with distinct machine learning and choice to predict liver infection.