Comparison of artificial neural networks with logistic regression in prediction of kidney transplant outcomes

Predicting the outcome of a graft transplant with high level of accuracy is a challenging task. To answer the challenge, data mining can play a significant role. The goal of this study is to compare the performances and features of an Artificially Intelligent (AI)-based data mining technique namely Artificial Neural Network with Logistic Regression as a standard statistical data mining method to predict the outcome of kidney transplants over a 2-year horizon. The methodology employed utilizes a dataset made available to us from a kidney transplant database. The dataset embodies a number of important properties, which make it a good starting point for the purpose of this research. Results reveal that in most cases, the neural network technique outperforms logistic regression. This study highlights that in some situations, different techniques can potentially be integrated to improve the accuracy of predictions.