Liver Disease Prediction Using Machine Learning Algorithms with Comparative Analysis of Different Algorithms

Today's diseases are more prevalent due to our lifestyle choices, eating habits, and other factors. Of all these illnesses, liver infections or disorders are the leading cause of all-cause mortality, affecting a sizable population of people inside and beyond the human race. Several factors that affect the liver are to blame for this condition. Being overweight, having an unidentified hepatitis illness, and consuming large amounts of alcohol are some of the factors that contribute to developing liver disease. This is the cause of many other symptoms, including aberrant nerve function, blood vomiting or coughing, kidney and liver failure, jaundice, and hepatic encephalopathy. The condition itself is quite costly and difficult to diagnose. Using predictive machine learning techniques, it is possible to improve accuracy while lowering the high cost of identification. We must determine a person's risk factor utilizing a blood sample and prediction algorithms. In this paper, we investigate four prediction methods: decision tree, logistic regression, random forest, and support vector machine. Additionally, the use of clinical data for the computation of liver disease was the main focus of our work. Through our analysis and patient's long-term sickness prediction, we also looked at a number of representational frameworks.