Neural network based decision support system that detects for newborn urinary tract infection

Nowadys in the world hundreds of infants are effected by Urinary Track Infection which causes seriously disorders in the long term. Thus early stage diagnosis is very important in terms of newborn's healthy and treatment. Therefore in this thesis studied on a data set obtained from a hospital newborn intensive care unit. With artificial neural networks and support vector machines in this study it is intended to create a decision support system. Within this study, It is aimed to create a decision support system by using artificial neural networks support vector machines and a few algorithm for correlation. There are two studies carried out within the artificial neural networks which are 1 fold and 3 fold. As a result of conducted tests it is seen that PNN method which is applied for 3 fold with 91.4251 ratio gives the best result for the test. As for education, it is seen that MLNN-2 method which is applied for 3 fold with 98.9130 ratio gives the best result. The study of neural networks and support vector machines with no appreciable accuracy of the classification process was concluded to be successful. Keywords: Artificial neural networks, Urinary tract infection, Decision Support System, Newborn, Flexible Computing and Bioinformatics Techniques