An ensembling approach to predict hepatitis in patients with liver disease using machine learning

Abstract

With a 3.5% mortality rate, liver disease is one of the worst diseases in existence. Pakistan is targeting this major health issue from several perspectives, to improve prevention, diagnosis, and treatment due to having the highest incidence of liver disorders in the world. For liver problem disease, also known as HEP C, Pakistan is now the second most prevalent country in the world. This is due to the rapid progression of HEP C, which can only be stopped by early diagnosis. If not, it progresses to the last stage of HEP C cirrhosis, which has no other treatment options besides liver transplantation. One and only machine learning algorithms like logistic regression, random forest, KNN, K-Means, and XGBoost can be used to predict liver illness utilizing modern methods like artificial intelligence. Data is gathered from Kaggle and subjected to several machine learning algorithms after pre-processing in order to quickly diagnose liver disease. Additionally, to improve accuracy, all of these algorithms are ensemble, and accuracy is 78.96%, along with precision, recall, and F1 score. In this work, liver disease is predicted early on using pre-processing, feature extraction, and classification techniques. Recall, precision, and f1score metrics are used to compare the accuracy of the six algorithms, and these algorithms are then combined to provide the most accurate diagnosis of liver disease.