Published Paper Details:

Liver disease has become a prominent global health concern, with conditions like cirrhosis and liver cancer ranking among the leading causes of mortality worldwide. The insidious nature of many liver diseases often results in asymptomatic onset, leading to underdiagnosis and delayed treatment. Early detection and management are pivotal in mitigating the impact of liver illnesses. Recognizing the challenges posed by the costly and intricate diagnostic processes, this study aimed to evaluate the effectiveness of diverse machine learning techniques in identifying liver disease. UT disease. Utilizing liver patient record dataset, this research explored five machine learning models for predicting the occurrence of liver disease using patients' medical histories. Through meticulous data pre-processing and analysis, encompassing tasks such as handling Managing absent data, encoding categorical variables, and standardizing features., the dataset was meticulously prepared for model training. Subsequentaluation of the Five algorithms for machine learning, restated. revealed Random Forest as the top-performing model, achieving an accuracy of 75.87% on the test dataset. This research underscores the promise of machine learning in accurately predicting liver disease, thereby facilitating early diagnosis and intervention.