Comparison of Supervised Machine Learning Algorithms for Predicting Liver Disease

Abstract

Chronic Liver Disease (CLD) is the main cause of death worldwide, affecting a large number of people. This is a serious illness caused by a variety of factors that affect the liver Obesity, undetected hepatitis, and alcohol abuse are just a few examples. This is the cause of aberrant nerve function, blood in the cough or vomit, renal failure, liver failure, jaundice, liver encephalopathy, and many other symptoms. The diagnosis of this condition is both expensive and time-consuming. As a result, the purpose of this research is to assess the efficacy of various Machine Learning algorithms in order to lower the high cost of chronic liver disease diagnosis through prediction. We employed six different algorithms in this study: Logistic Regression, K Nearest Neighbors, Decision Tree, Support Vector Machine, Nave Bayes, and Random Forest. Different measurement approaches, such as accuracy, precision, recall, f-1 score, and specificity, were used to assess the performance of different categorization algorithms. For LR, RF, DT, SVM, KNN, and NB, the accuracy was 75 percent, 74 percent, 69 percent, 64 percent, 62 percent, and 53 percent, respectively.  The research revealed that the LR had the best accuracy. Furthermore, the current study primarily focused on the use of clinical data for liver disease prediction, and we used our research to investigate several ways of expressing such data.