Enhancing Liver Health Diagnostics with Machine Learning: A Comparative Analysis of Classifiers

Liver is a substaintial organ, which plays a crucial role in supporting body functions. However, it has turned into a critical health disorder on the scale of Global health problem which is known as Liver Fibrosis/Cirrhosis. It has become extremely difficult to predict before-hand the present condition of liver. In traditional way to predict the stage of Liver Fibrosis/Cirrhosis, it is a long-term time taken process and if we delay it leads to Liver Cancer. In this research, to predict the early stage of Liver Fibrosis/Cirrhosis, we approach machine learning techniques.The research aims to focus on various supervised machine learning models, including the Support Vector Classifier (SVC), MLP, Logistic Regression, Decision Tree (DT) Classifier, Random Forest (RF) Classifier, Gradient Boosting Classifier, LGBM Classifier, and XGB Classifier. These techniques evaluates the dataset for accuracy, recall, precision and f1-score. Among all models XGB Classifier achieved with the accuracy of $\mathbf{9 9 \%}$,positioning it as an optimal model for early diagnosis and preventative action for medical response.