Prediction of 5 Categories of Hepatitis Disease using Machine Learning

The primary objective of this research is to identify the most effective tool for diagnosing and detecting Hepatitis, as well as predicting the life expectancy of Hepatitis patients. To achieve this goal, we conducted a comprehensive comparative study involving various machine learning tools and neural networks. Our evaluation is primarily based on two critical performance metrics: accuracy rate and mean square error. In our study, we focused on three prominent Machine Learning (ML) algorithms: Support Vector Machines (SVM), K Nearest Neighbor (KNN), and Artificial Neural Network (ANN). These algorithms were chosen as they have demonstrated promise in the realm of medical diagnosis and prediction. We systematically assessed their performance in diagnosing Hepatitis disease based on their prediction accuracy. The results of this research will contribute valuable insights into selecting the most suitable tool for Hepatitis diagnosis and prognosis, with the ultimate goal of improving patient care and outcomes. By analyzing and comparing these ML algorithms and neural networks, we aim to advance the field of medical diagnosis and prediction in the context of Hepatitis management.

Keywords: Support Vector Machines (SVM), K nearest Neighbor (KNN) and Artificial Neural Network (ANN)