Liver Cirrhosis Prediction using Machine Learning Approaches

Abstract

Liver cirrhosis is a highly infectious blood-borne illness that is often asymptomatic in its early stages. As a result, diagnosing and treating patients during the early stages of illness is challenging. As the illness progresses to its latter stages, diagnosis and therapy become increasingly challenging. The purpose of this work is to offer an artificial intelligence system based on machine learning algorithms that may assist healthcare practitioners in making an early diagnosis of liver cirrhosis. Various machine learning algorithms are being developed with this in mind to forecast the possibility of a liver cirrhosis infection. In this research, three alternative models for reliable prediction were produced by training three separate models employing a range of physiological parameters and machine learning methods such as Support Vector Machine, Decision Tree Classification, and Random Forest Classification. Random Forest was the best performing algorithm in this challenge, with an accuracy of around 97 percent. The open-access Liver Cirrhosis data dataset was employed in the method's development. The accuracy percentage of the models employed in this study is substantially greater than in earlier research, showing that the models utilized in this study are more dependable. Several model comparisons have shown their robustness, and the scheme may be determined from the research analysis.