Classifying Liver Disease With Boosting Machine Learning Approaches

Liver diseases pose a significant global health challenge due to their impact on metabolic function and the difficulty of early detection. Traditional diagnostic methods such as liver biopsy have limitations due to their invasive nature and high costs. This research examines the application of advanced machine learning techniques such as Gradient Boosting, AdaBoost, XGBoost and CatBoost for classification of liver diseases using a publicly available dataset of 1700 clinical records. Statistical analyses identified key predictors such as age, body mass index (BMI), lifestyle factors, and liver function tests, which were used to train and evaluate the models. The performance of the models was evaluated using metrics such as accuracy, precision, recall and AUC-ROC. The CatBoost model showed the highest performance with an accuracy of 93.82%, while also producing the most consistent results with precision (91.97%), recall (96.62%), F1 score (94.25%) and AUC-ROC (95.64%). These results highlight the potential of machine learning-based approaches to improve diagnostic accuracy and reduce reliance on invasive procedures. The proposed framework can contribute to improving patient outcomes and optimizing healthcare resources by providing a foundation for real-time clinical decision support systems.