Liver Cirrhosis Prediction using Machine Learning

This study presents a liver cirrhosis prediction project utilizing machine learning algorithms in healthcare to enhance diagnosis and treatment. A model based on XGBoost was developed, achieving a prediction accuracy of 79.87%. The model identified critical features for predicting cirrhosis and can support medical professionals in early identification and intervention. Future research can focus on expanding the dataset, incorporating genetic and lifestyle factors, and integrating the model into clinical settings as an additional diagnostic tool. This work underscores the potential of machine learning in healthcare for improving patient outcomes.