Intelligent Disease Prediction System for Hepatitis C Patients

Abstract

Accurate and timely predictions are essential for minimizing the devastating side effects of
medical therapies, especially when dealing with serious illnesses like hepatitis C. In this research,
a machine learning-based classification framework has been proposed to enable more reliable
predictions of treatment responses in hepatitis C patients. The focus of this framework is to
explore the potential of Machine Learning Techniques (MLT) in predicting, forecasting, and
treating chronic diseases such as tumors, hepatitis, and heart diseases. In the proposed model, five
ML algorithms - Naïve Bayes (NB), Decision Tree (DT), Bayesian Nets (BNs), Support Vector
Machine (SVM), and Random Forest (RF) - are employed to predict the outcomes of hepatitis C
patients undergoing treatment. The AI-enabled medical services model that has been developed is
capable of delivering accurate predictions for hepatitis C with improved results in the future.
Furthermore, the framework can be further enhanced by including additional ML techniques, such
as deep learning or reinforcement learning, to achieve even more accurate results