Predictive Modeling for Liver Disease Diagnosis Using Machine Learning Techniques

The early detection and accurate prediction of liver disease have become a critical focus due to the increasing prevalence of liver-related disorders. Identifying patterns in medical data to enhance diagnosis and prognosis is one of the major challenges in this domain. The exploration of Machine Learning (ML) algorithms for liver disease prediction has been driven by their promising results in various healthcare applications. This survey explores and evaluates the current machine learning models utilized for liver disease prediction to provide an overview of them. It also highlights potential areas that need improvement. This article assesses the reliability, performance, and effectiveness of various ML methodologies, including ensemble learning, decision trees, support vector machines (SVMs), and deep learning techniques, in the context of liver disease diagnosis