Paper Title
Liver Disease Prediction Using Artificial Intelligence

Abstract
The diagnosis of liver illnesses may be made using several conventional techniques, but they are costly. By offering early treatment, early detection of liver illness would help everyone who is at risk for liver disease. As innovation develops, machine learning will have a significant influence on healthcare since it can predict ailments in their early stages. In our daily lives, artificial intelligence (AI) is being used more and more frequently, including in healthcare. We now have faster access to a plethora of fresh data on patients' chronic liver illnesses, such as non-alcoholic fatty liver disease and liver fibrosis, because of artificial intelligence (AI). This study determines the predictive capacity of machine learning, the application of artificial intelligence, for liver disease. The liver disease prediction (LDP) approach, which can be used by researchers, students, stakeholders, and health professionals to forecast liver illness, is introduced in this work. Linear Discriminant Analysis, Classification and Regression Trees, Naive Bayes, Support Vector Machines, and K-Nearest Neighbors are the five approaches that are selected. R and Python are used to assess the accuracy and determine which classification technique best predicts liver illness. The results showed that K-NN achieved the maximum accuracy of 92.1%, while the auto-encoder network achieved an accuracy of 93.2%, which is more than acceptable and might be considered for the prediction of liver illness. Keywords - AI, liver disease, Data Analysis, Prediction, Machine Learning, Algorithms.