Chronic Liver Diseases and Stage Detection Using Hybrid Machine Learning Model

Abstract

Liver disease risk has been rising rapidly among people over the past several decades and is thought to be one of the world's most lethal diseases. To forecast the disease using vast medical datasets is a challenging issue for academics. They have developed machine learning strategies like classification and clustering to address this problem. The primary goal of this research is to use classificational algorithms to predict a patient's likelihood of getting liver disease. Additionally, it indicates the stage of the liver illness, such as Cirrhosis Liver, Liver Fibrosis, Fatty Liver, and Healthy Liver. Accordingly, the suggested Hybrid Classifier (RF,SVC,XGBoost) and the algorithms NB, SVM, LOR,RF,DT,KNN, and RBTC are evaluated for classification accuracy and processing speed. Using these With 99% accuracy, the Hybrid Classifier, which is a superior classifier, is selected after taking performance aspects into account.