Ensemble learning model for Classification of Hepatitis C Disease

Abstract

Supervised machine learning is gaining prominence in bioinformatics, particularly in the context of disease diagnosis. This discipline falls under the broader umbrella of artificial intelligence (AI). Hepatitis disease is a leading cause of death, with Hepatitis C being particularly concerning due to the absence of a vaccine. The transmission of Hepatitis C primarily occurs through blood transfusions, contaminated needles, and unsterilized medical instruments. Accurate diagnosis and prediction of Hepatitis C virus (HCV) infection are crucial for effective treatment of affected individuals. Traditional clinical approaches may lead to misdiagnosis in hepatitis cases. Machine learning technologies are enhancing the healthcare sector by improving the accuracy of disease diagnosis and prognosis. This research introduces a hybrid ensemble model aimed at predicting and classifying data related to HCV patients. The dataset utilized, known as HCV+data, is sourced from the UCI machine learning repository. Four classification algorithms such as logistic regression, support vector machine, decision tree, and K-nearest neighbour were employed in the training process. A hybrid ensemble model is created using the majority voting method to integrate various weak or base classification learners. Results demonstrate that the ensemble learning model achieves superior accuracy compared to single-learner machine learning algorithms, with a classification accuracy of 94.07% for hepatitis patients. This model is expected to assist healthcare professionals in accurately diagnosing complex and progressive diseases.