Abstract: The incidence of disease caused to the liver has increased rapidly due to excessive alcohol consumption, inhalation of polluted air, having contaminated food so a medical professional program should support the doctor to predict the disease automatically. By the recursive development of technology in artificial intelligence, prior diagnosis of liver disease could be done, so people could diagnose easily fatal disease in early stages. This would greatly help the health care community, and a specialist diagnosis system can be used in a remote location. The liver has a vital role in human health and helps in the removal of unwanted chemicals and toxins from the human body. Therefore, prior detection has a major role in diagnosis and recovery. Various types of machine learning methods that are used to diagnose liver disease are KNN, NB, DNN, SVM, K-Mean and DT, etc. Which provides each individual accuracy and sensitivity. The objective of this paper is to present a survey and analysis of all diagnostic techniques for liver diseases diagnosis in the medical field, which are already being used for predicting liver disease by different experts and the analysis will be based on accuracy, sensitivity, and clarity.

Keywords: Machine Learning, LR-Logistic Regression, KNN- K Nearest Neighbor, DT-Decision Tree, NB- Naïve Bayes, RF- Random Forest, ANN-Artificial Neural Network, SVM- Super Vector Machine, EL-Ensemble Learning.

| DOI: 10.17148/IARJSET.2022.94113