Artificial Neural Networks in Prediction of Patient Survival after Liver Transplantation

Abstract

Predicting the survival of patients after liver transplantation is one of the challenging areas in the field of medicine. The ultimate curative treatment for the last stage liver disease is the liver transplantation. While going for any transplantation, everybody will think about the survival. This paper summarizes the prediction of survival of patients undergoing liver transplantation in both computing and clinical manner. We proposed an Artificial Neural Network model to define three month mortality of patients after liver transplantation using United Network for Organ Sharing dataset. We trained the data using Multilayer Perceptron Artificial Neural Network model using 10 fold cross validation and achieved an accuracy of 99.74%. The comparison of our model was done with other Artificial Neural Network models with the help of various performance error measures. In order to ensure accuracy produced by the model, we also made comparison with existing models in the prediction of survival of patients after liver transplantation.