Liver disease is a serious health problem that affects millions of people around the world and can lead to severe complications if not diagnosed at an early stage. Timely detection of liver disorders is essential for effective treatment and better patient outcomes. However, traditional diagnostic methods often require multiple laboratory tests, medical imaging, and expert evaluation, which can be time-consuming and expensive. With the rapid growth of Artificial Intelligence (AI) and Machine Learning (ML), intelligent healthcare systems are emerging as valuable tools for supporting medical diagnosis and improving healthcare services.

This study proposes a machine learning-based system for predicting liver disease using patient clinical and biochemical data. The system utilizes important health parameters such as age, gender, bilirubin levels, liver enzyme measurements, protein levels, and albumin-globulin ratio to determine the likelihood of liver disease. Before model development, the dataset is preprocessed through data cleaning, handling missing values, normalization, and feature selection to improve prediction accuracy and reliability.

Several machine learning algorithms, including Logistic Regression, Decision Tree, Random Forest, Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and XGBoost, are trained and evaluated to identify the most effective approach for liver disease prediction. The performance of these models is assessed using standard evaluation metrics such as accuracy, precision, recall, F1-score, and ROC-AUC score. A comparative analysis is conducted to determine which algorithm provides the best balance between predictive performance and computational efficiency.

Keywords— Liver Disease, Machine Learning, Artificial Intelligence, Healthcare Analytics, Disease Prediction, Random Forest, XGBoost, Early Diagnosis, Predictive Modeling, Clinical Decision Support.