Prediction of Liver Disease using Machine Learning Models with PCA

The liver is one of the most vital organs of the human body. There are various disorders of liver that need early treatment by doctors. Early diagnosis and treating the patients are significant to reduce the risk. Healthcare system can benefit from various Machine Learning (ML) models to predict diseases in early stage. The aim of this study is to predict liver disease using different ML models applied on Indian Liver Patient Dataset (ILPD). The models used on this work are Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Random Forest (RF), Artificial Neural Network (ANN) and various versions of Ensemble Learning (EL). The results show that ensemble learning of KNN, RF, and SVM achieved the highest accuracy of 88%. Moreover, ensemble learning of KNN with RF obtained the highest True Positive Rate (TPR) of 99% on negative cases. In addition, this paper found that the Principal Component Analysis (PCA) technique has good impact to increase the accuracy.