Abstract

Liver illness, affecting the human body primarily in the liver, is one of the most severe diseases. The liver plays a crucial role in waste removal, vitamin storage, and digestion. Early detection is vital in mitigating the risks associated with this lethal disease and potentially saving lives. Approximately 3.5 percent of the global population is affected by liver illness. Advancements in disease detection, particularly using machine learning classification techniques, have shown promise in improving outcomes. Other machine learning methods like artificial neural networks and convolutional neural networks are also being employed to address this challenge. These methods aim to increase the life expectancy of affected patients and prevent the development of chronic liver disease (CLD). The widespread use of barcodes, automation in commercial and government transactions, and advancements in data gathering systems have led to the accumulation of vast amounts of data. In response, proposed models utilize ensemble methods such as random forest, ADA boost, and gradient boost to achieve higher accuracy in disease detection. By combining these techniques, the model aims to enhance diagnostic capabilities and improve patient outcomes.