Liver Damage Prediction: Using Classification Machine Learning Models

Abstract-Liver diseases like cirrhosis and hepatitis are major causes of global morbidity and mortality, highlighting the need for early detection. Traditional diagnostic methods often identify liver damage at later stages, limiting preventive interventions. This study develops a machine learning model to predict liver damage earlier using clinical features and lab results. By analyzing a data-set with patient demographics and biochemical markers, we apply machine learning algorithms, including Random Forest, Decision Tree, and Logistic Regression, and evaluate their performance using metrics like accuracy, precision, recall, F1 score, and ROC-AUC. The Random Forest model outperformed others, showing high accuracy and robustness. Feature importance analysis revealed critical clinical factors, such as serum bilirubin and liver enzymes, in predicting liver damage. These results suggest that machine learning, especially Random Forest, could aid in the early detection of liver disease, improving patient outcomes. Future work will focus on using larger, more diverse data-sets and advanced models to improve predictive accuracy.