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

Koukouvinos, C; Parpoula, C; Theodoraki, E-M

dc.contributor.author	Koukouvinos, C	en
dc.contributor.author	Parpoula, C	en
dc.contributor.author	Theodoraki, E-M	en
dc.date.accessioned	2014-03-01T02:08:22Z
dc.date.available	2014-03-01T02:08:22Z
dc.date.issued	2012	en
dc.identifier.issn	17526418	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/29648
dc.subject	Classification trees	en
dc.subject	Data mining	en
dc.subject	Medical data	en
dc.subject	Outcome prediction	en
dc.subject	ROC analysis	en
dc.subject.other	Classification algorithm	en
dc.subject.other	Classification methods	en
dc.subject.other	Classification trees	en
dc.subject.other	Data sets	en
dc.subject.other	Demographic data	en
dc.subject.other	Medical data	en
dc.subject.other	Medical decision making	en
dc.subject.other	Outcome prediction	en
dc.subject.other	Receiver operating characteristics analysis	en
dc.subject.other	ROC analysis	en
dc.subject.other	Trauma patients	en
dc.subject.other	Forecasting	en
dc.subject.other	Learning algorithms	en
dc.subject.other	Trees (mathematics)	en
dc.subject.other	Data mining	en
dc.title	Classification methods and ROC analysis for outcome prediction of patients following injuries	en
heal.type	journalArticle	en
heal.identifier.primary	10.1504/IJBET.2012.045357	en
heal.identifier.secondary	http://dx.doi.org/10.1504/IJBET.2012.045357	en
heal.publicationDate	2012	en
heal.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. Copyright © 2012 Inderscience Enterprises Ltd.	en
heal.journalName	International Journal of Biomedical Engineering and Technology	en
dc.identifier.doi	10.1504/IJBET.2012.045357	en
dc.identifier.volume	8	en
dc.identifier.issue	1	en
dc.identifier.spage	49	en
dc.identifier.epage	59	en