Bayesian decision trees for predicting survival of patients: a study on the US National Trauma Data Bank

2.50
Hdl Handle:
http://hdl.handle.net/10547/293690
Title:
Bayesian decision trees for predicting survival of patients: a study on the US National Trauma Data Bank
Authors:
Schetinin, Vitaly ( 0000-0003-1826-0153 ) ; Jakaite, Livija; Jakaitis, Janis; Krzanowski, Wojtek
Abstract:
Trauma and Injury Severity Score (TRISS) models have been developed for predicting the survival probability of injured patients the majority of which obtain up to three injuries in six body regions. Practitioners have noted that the accuracy of TRISS predictions is unacceptable for patients with a larger number of injuries. Moreover, the TRISS method is incapable of providing accurate estimates of predictive density of survival, that are required for calculating confidence intervals. In this paper we propose Bayesian in ference for estimating the desired predictive density. The inference is based on decision tree models which split data along explanatory variables, that makes these models interpretable. The proposed method has outperformed the TRISS method in terms of accuracy of prediction on the cases recorded in the US National Trauma Data Bank. The developed method has been made available for evaluation purposes as a stand-alone application.
Affiliation:
University of Bedfordshire; University of Exeter
Citation:
Schetinin, V., Jakaite, L., Jakaitis, J., Krzanowski, W. (2013) 'Bayesian Decision Trees for predicting survival of patients: a study on the US National Trauma Data Bank', Computer Methods and Programs in Biomedicine, 111(3), pp. 602- 612
Journal:
Computer Methods and Programs in Biomedicine
Issue Date:
2013
URI:
http://hdl.handle.net/10547/293690
DOI:
10.1016/j.cmpb.2013.05.015
Additional Links:
http://linkinghub.elsevier.com/retrieve/pii/S0169260713001727
Type:
Article
Language:
en
ISSN:
0169-2607
Appears in Collections:
Centre for Research in Distributed Technologies (CREDIT)

Full metadata record

DC FieldValue Language
dc.contributor.authorSchetinin, Vitalyen_GB
dc.contributor.authorJakaite, Livijaen_GB
dc.contributor.authorJakaitis, Janisen_GB
dc.contributor.authorKrzanowski, Wojteken_GB
dc.date.accessioned2013-06-10T09:46:24Z-
dc.date.available2013-06-10T09:46:24Z-
dc.date.issued2013-
dc.identifier.citationSchetinin, V., Jakaite, L., Jakaitis, J., Krzanowski, W. (2013) 'Bayesian Decision Trees for predicting survival of patients: a study on the US National Trauma Data Bank', Computer Methods and Programs in Biomedicine, 111(3), pp. 602- 612en_GB
dc.identifier.issn0169-2607-
dc.identifier.doi10.1016/j.cmpb.2013.05.015-
dc.identifier.urihttp://hdl.handle.net/10547/293690-
dc.description.abstractTrauma and Injury Severity Score (TRISS) models have been developed for predicting the survival probability of injured patients the majority of which obtain up to three injuries in six body regions. Practitioners have noted that the accuracy of TRISS predictions is unacceptable for patients with a larger number of injuries. Moreover, the TRISS method is incapable of providing accurate estimates of predictive density of survival, that are required for calculating confidence intervals. In this paper we propose Bayesian in ference for estimating the desired predictive density. The inference is based on decision tree models which split data along explanatory variables, that makes these models interpretable. The proposed method has outperformed the TRISS method in terms of accuracy of prediction on the cases recorded in the US National Trauma Data Bank. The developed method has been made available for evaluation purposes as a stand-alone application.en_GB
dc.language.isoenen
dc.relation.urlhttp://linkinghub.elsevier.com/retrieve/pii/S0169260713001727-
dc.subjectG760 Machine Learningen_GB
dc.subjectG311 Medical Statisticsen_GB
dc.subjectBayesian predictionen_GB
dc.subjectsurvival probabilityen_GB
dc.subjectMarkov chain Monte Carloen_GB
dc.subjectclassification treeen_GB
dc.subjecttrauma careen_GB
dc.titleBayesian decision trees for predicting survival of patients: a study on the US National Trauma Data Banken
dc.typeArticleen
dc.contributor.departmentUniversity of Bedfordshireen_GB
dc.contributor.departmentUniversity of Exeteren_GB
dc.identifier.journalComputer Methods and Programs in Biomedicineen_GB
This item is licensed under a Creative Commons License
Creative Commons
All Items in UOBREP are protected by copyright, with all rights reserved, unless otherwise indicated.