Diagnosis of Hepatitis-Related Illnesses using Machine Learning K.G.S.Venkatesan 1 , Tahera Abid 2 , Zahoora Abid 3 1 Department of Computer Science & Engineering, Megha Institute of Engineering & Technology for Women, Hyderabad, Telangana, India. 2 Department of Information Technology, Nawab Shah Alam Khan College of Engineering & Technology, Hyderabad, Telangana, India. 3 Department of Computer Science & Engineering, Nawab Shah Alam Khan College of Engineering & Technology, Hyderabad, Telangana, India. Received: 15.07.2023 Accepted: 21.07.2023 Published Online: 31.07.2023 Abstract: Hepatitis is inflammation of the liver’s tissue and is often brought on by an infection. Several research efforts have been made to create machine learning algorithms for the diagnosis of hepatitis disease. However, the link between hepatitis and its symptoms is seldom discussed. The primary goal of this research was to describe in detail a dataset of hepatitis symptoms culled from actual cases. The study authors also suggested creating a standalone classification platform that uses random forest support vector machine algorithms and decision tree to differentiate between healthy and diseased individuals. To do this, we would choose applicable variables and enclose them in a malleable wrapper. Some traits have been proven to correlate highly with a hepatitis diagnosis. This article describes a technique that has the potential to enhance early-stage hepatitis detection, which might lessen the disease’s devastating impact on human life. Remember that of the three methods RF achieved the best accuracy and maintained its superiority across all datasets with very little variation. Key words: Automated hepatitis diagnosis, Adaptive feature selection, Hepatitis symptoms, Support vector machine. Correspondence: Professor, Department of Computer Science & Engineering, Megha Institute of Engineering & Technology for Women, Hyderabad, Telangana, India. Email:drkgsvenkatcse@meghaengg.ac.in https://doi.org/10.58599/IJSMIEN.2023.1705 Volume-1, Issue-7, PP:40-50 (2023) This work is licensed under a Creative Commons Attribution 4.0 International License CC BY-NC-ND 4.0. 40