Machine Learning based Prediction of Liver Disease

Liver is one of the most important organs in the human body. It plays crucial roles in protein synthesis, digestion, storage and excretion of several minerals and proteins. Hence, liver diseases have devastating effects on the human body. Modern medical science provides ways to predict and diagnose, however, machine learning (ML) could aid in liver disease detection. In this work, various ML models such as Naive Bayes, Support Vector Machine, Logistic Regression, Decision Tree and Random Forest Classifier, K-Nearest Neighbours Classifier, Kernel SVM, and XGBoost have been implemented on Liver Disease Patient Dataset from Kaggle to predict the possibility of chronic liver disease. Also, several parameters such as accuracy, precision, recall, F1-score, and confusion matrix were calculated for the evaluation of the work. The results conclude that XGBoost has outperformed all other classification models with 99.5% accuracy.