Factors like obesity, alcohol consumption, viral infections, and high cholesterol are rapidly increasing in humans and causing various diseases. One of them is a liver illness, which is highly serious because the liver is fundamental to human survival. Liver disease continues to be a global healthcare challenge and is increasing day by day. Till now detection of liver illness is crucial for the proper course of therapy. Advanced technologies like deep and machine learning are used to predict liver illness. This essay offers a thorough evaluation of current methods for detecting liver illness. Various machine learning algorithms are applied in medical science to predict diseases like liver disease, heart disease, etc. Till now algorithms like Logistic Regression, Random Forest, and REPTree have been used which give excellent performance on datasets. It discusses various classification algorithms, including J48, Naive Bayes, SMO, Random Forest, Logistic Regression, and IBk, highlighting their key characteristics and usage scenarios. The review also outlines the steps involved in a typical classification workflow, from database selection to performance evaluation. This paper explores rising trends in liver disease detection, the potential for precision medicine approaches is also highlighted, as an overview of the current state of liver disease detection and the future scope of research in the field.