Neural networks for prediction of trauma victims´ outcome. comparison with the TRISS and Revised Trauma Score

Last decades predictive models that assess probability of survival for trauma victims have been developed. Some of the most commonly used are the TRISS methodology, the logistic regression modelling technique, and the Revised Trauma Score which derive from specific input variables. However recently, the development of neural network models reveal encouraging results as they most of the times outperform the traditional approaches. In this paper we present models´ predictability comparing the Area Under the Curve and we discuss the results.