Performance Assessment of Various Machine Learning Methods for Prediction Liver Disease

Abstract

Chronic Liver Disease (CLD) is the leading cause of death worldwide, affecting a large number of people. A variety of factors damage the liver, resulting in this disease. Obesity, undiagnosed hepatitis, and alcohol abuse are only a few examples. This is the cause of irregular nerve activity, blood in the cough or vomit, kidney failure, liver failure, jaundice, liver encephalopathy, and many other symptoms. Therefore, the goal of this work is to evaluate the best algorithm find from different types of prediction algorithm using the values of predicted accuracy. In this work, I used six algorithms Logistic Regression, K Nearest Neighbors, Decision Tree, Support Vector Machine, Naive Bayes, and Random Forest. Different measurement techniques, such as accuracy, precision, recall, f-1 ranking, and specificity, were used to assess the performance of different classification techniques. The performance parameters, such as classification accuracy and execution time, are used to compare these classifier algorithms. According to the findings of the experiments, the RF and KNN are best classifier algorithms for predicting liver diseases.