Exploring Machine Learning Approaches in Liver Disease Diagnosis
Main Article Content
Abstract
Worldwide it has been observed that the count of patents with liver diseases has been consequently becoming widespread in the context of polluted environment, inhale of polluted gas, overuse of some drugs, packaged and contaminated foodstuffs and majorly drinking addictions., therefore an expert system in the medical department will be able to make an automatic prediction of the situation. Since there is no doubt that machine learning technology is coming up with better and better results, it is now feasible for early detection of chronic liver disease, that way, people can get the disease diagnosed when it becomes fatal. As the population of elderly individuals grows, a system that provides more expertise in medical care and an expert system for medicine located in a distant location will come in handy. The motive of this study is to evaluate the effectiveness and performance of various machine learning algorithms in predicting chronic liver disease, with the aim of reducing the high costs associated with its diagnosis. A range of machine learning approaches are presented in a comprehensive survey as a part of this work. These approaches are of prime importance in the diagnosis of liver disease. The notable machine learning algorithms used in this work demonstrate different degrees of sensitivity, precision and accuracy. The primary objective of this work is twofold: first, to give a complete survey of existing techniques on liver disease prediction; second, to carry out a comparative analysis of performance of the machine learning algorithms used in performance analysis. Through synthesizing insights from different algorithms, the goal is to enrich the knowledge of efficient methods for liver disease diagnosis and prediction in the medical field.