Volume -15 | Issue -1
Volume -15 | Issue -1
Volume -15 | Issue -1
Volume -14 | Issue -6
Volume -14 | Issue -6
Due to the quick rise in liver illness caused by excessive alcohol use, contaminated gas inhalation, drug use, tainted food, and pickled food packaging, a doctor can make an automatic forecast with the aid of a medical expert system. Early liver disease prediction is now attainable because to the consistent advancements in machine learning technology, allowing for simple early identification of the fatal condition. This will make healthcare more beneficial, and a medical expert system can be employed in a remote location. The liver is vital to life and promotes the body's ability to rid itself of poisons. Early detection of the condition is therefore crucial for recovery. many machine learning techniques, including supervised, unsupervised, and semi-supervising, bolstering SVM, KNN, K Mean clustering, neural networks, decision trees, and other learning techniques for diagnosing liver disease provide varying accuracy, precision, and sensitivity. The goal of this paper is to provide an overview and comparative analysis of all machine learning techniques currently being used in the medical field for the diagnosis and prediction of liver disease. The analysis is based on accuracy, sensitivity, precision, and specificity.