For the current REF see the REF 2021 website REF 2021 logo

Output details

11 - Computer Science and Informatics

University of Bedfordshire

Return to search Previous output Next output
Output 0 of 0 in the submission
Article title

Bayesian Decision Trees for predicting survival of patients: A study on the US National Trauma Data Bank

Type
D - Journal article
Title of journal
Computer Methods and Programs in Biomedicine
Article number
-
Volume number
111
Issue number
3
First page of article
602
ISSN of journal
01692607
Year of publication
2013
URL
-
Number of additional authors
3
Additional information

<13> The “gold-standard” method for predicting survival in trauma care has been criticised for unexplained fluctuation in predictions. The paper reports the first evidences of successful application of the Bayesian method to the largest national trauma data including 0.5 million patients, which has significantly outperformed the existing method. The developed software and open source were made available via http://www.traumacalc.org/bc2/, and the files have been downloaded 2,195 times since February 2013. A leading surgeon Prof Osler at the University of Vermont has invited to compare the method with those developed in his research group.

Interdisciplinary
-
Cross-referral requested
-
Research group
T - Centre for Research in Distributed Technologies
Citation count
0
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-