Liver diseases have become increasingly lethal in numerous countries, with patient numbers rising due to factors such as alcohol consumption, inhalation of harmful gases, and ingestion of contaminated food and drugs. This study focuses on developing predictive models for liver disorders using liver patient datasets, aiming to alleviate the workload on healthcare professionals. The dataset, sourced from the UCI Repository, encompasses supervised learning data from patients undergoing medical examinations. By leveraging historical patient data, the study utilizes machine learning and deep learning algorithms to predict liver disease outcomes. Specifically, Decision Tree, K-Nearest Neighbour (KNN), and Artificial Neural Network (ANN) algorithms were applied to assess their predictive capabilities. Results indicate that the Decision Tree algorithm achieved a notable accuracy of 99.96%, making it the most precise model for liver disease prediction. The KNN algorithm followed with an accuracy of 97.42%, while the ANN model attained an accuracy of 71.55%. These findings suggest that machine learning and deep learning algorithms can effectively predict liver diseases, providing valuable tools for clinical decision-making and improving patient outcomes.