Enhancing Hepatitis B Treatment Decision Using Machine Learning Techniques in Egypt

Abstract

Advancements in artificial intelligence (AI), particularly machine and deep learning models, provide enhanced methodologies for healthcare diagnosis and treatment decision-making, particularly in liver disease. Hepatitis B poses a significant global health challenge; this research introduces an adaptive machine learning framework to support decision-making in hepatitis B treatment. This study compares various models utilizing clinical data from 700 Egyptian patients across six decision points. Among the models evaluated, neural networks, gradient boosting, and random forest demonstrated superior and consistent performance, with high precision (> 0.75), recall (>0.98), F1-score (>0.82), and accuracy (>0.728).