Title: Classification methods and ROC analysis for outcome prediction of patients following injuries

Authors: C. Koukouvinos; C. Parpoula; E.-M. Theodoraki

Addresses: Department of Mathematics, National Technical University of Athens, Zografou 15773, Athens, Greece. ' Department of Mathematics, National Technical University of Athens, Zografou 15773, Athens, Greece. ' Department of Statistics and Actuarial-Financial Mathematics, University of the Aegean, Karlovassi 83200, Samos Island, Greece

Abstract: Receiver Operating Characteristics (ROC) analysis is commonly used in medical decision making, and in recent years has been used increasingly in machine learning and data-mining research. In this study, it is used for assessing the performance of classification algorithms in predicting trauma patients outcome. Data set comprised 8544 severely injured patients who had been admitted to Hellenic hospitals from the year 2005 to 2006. We analysed the demographic data and the factors that may have influenced the outcome in the group of patients with trauma and several combinations of significant factors were determined for that purpose.

Keywords: data mining; classi?cation trees; ROC analysis; medical data; outcome prediction; receiver operating characteristics; medical decision making; trauma patients; patient outcomes; severe injuries; Greece.

DOI: 10.1504/IJBET.2012.045357

International Journal of Biomedical Engineering and Technology, 2012 Vol.8 No.1, pp.49 - 59

Published online: 12 Dec 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article