A Comparative Analysis of Classification Algorithms for Predicting Liver Cirrhosis Using Machine Learning

Among the majority of people in this world, liver cirrhosis is the primary cause of death. There are several factors that damage the liver and lead to this disease. For instance, alcohol abuse, obesity, and an undetected hepatitis infection. It is the cause of numerous other conditions, including aberrant nerve disorder, blood while coughing and vomiting, liver tissue and kidney disease, jaundice, and hepatic encephalopathy. Identifying this disease is quite difficult and costly. Thus, the objective is this process to assess effectiveness the several machine learning (ML)models with the aim of lowering high expenses associated with the diagnosis of liver cirrhosis through prediction. This paper used six different approaches: Random Forest (RF), K-Nearest Neighbour (KNN), Decision Tree (DT), Support Vector Machine (SVM), Naïve Bayes (NB), and Logistic Regression (LR).A range of measuring units, like as recall, f-1 score, accuracy, and precision, was used to evaluate various classification procedures. The Logistic Regression had the highest accuracy with 95%.