Volume 10, Issue 1, 2017, Pages 440 - 455
A decision tree based approach with sampling techniques to predict the survival status of poly-trauma patients
Authors
José Sanza, joseantonio.sanz@unavarra.es, Javier Fernandeza, Humberto Bustincea, Carlos Gradinb, Mariano Fortúnc, Tomás Belzuneguib, d
aDepartamento de Automatica y Computacion, Institute of Smart Cities, Universidad Publica de Navarra, Campus Arrosadia s/n, Pamplona, P.O. Box 31006, Spain
bDepartment of Health, Universidad Publica de Navarra, Barañain Avenue s/n, Pamplona, P.O. Box 31008, Spain
cAccident and Emergency Department, Hospital of Tudela, Carretera Tarazona, Km. 3, Tudela, Spain
dAccident and Emergency Department, Hospital of Navarre, Calle de Irunlarrea, 3E, Pamplona, Spain
Received 10 June 2016, Accepted 9 November 2016, Available Online 1 January 2017.
- DOI
- 10.2991/ijcis.2017.10.1.30How to use a DOI?
- Keywords
- Trauma patients; Survival prediction; Decision trees; Imbalanced classification problems; Sampling Techniques
- Abstract
Survival prediction of poly-trauma patients measure the quality of emergency services by comparing their predictions with the real outcomes. The aim of this paper is to tackle this problem applying C4.5 since it achieves accurate results and it provides interpretable models. Furthermore, we use sampling techniques because, among the 378 patients treated at the Hospital of Navarre, the number of survivals excels that of deaths. Logistic regressions are used in the comparison, since they are an standard in this domain.
- Copyright
- © 2017, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article under the CC BY-NC license (http://creativecommons.org/licences/by-nc/4.0/).
Download article (PDF)
View full text (HTML)
Cite this article
TY - JOUR AU - José Sanz AU - Javier Fernandez AU - Humberto Bustince AU - Carlos Gradin AU - Mariano Fortún AU - Tomás Belzunegui PY - 2017 DA - 2017/01/01 TI - A decision tree based approach with sampling techniques to predict the survival status of poly-trauma patients JO - International Journal of Computational Intelligence Systems SP - 440 EP - 455 VL - 10 IS - 1 SN - 1875-6883 UR - https://doi.org/10.2991/ijcis.2017.10.1.30 DO - 10.2991/ijcis.2017.10.1.30 ID - Sanz2017 ER -