Combining data and meta-analysis to build Bayesian networks for clinical decision support.
- Submitting institution
-
Queen Mary University of London
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 400
- Type
- D - Journal article
- DOI
-
10.1016/j.jbi.2014.07.018
- Title of journal
- J Biomed Inform
- Article number
- -
- First page
- 373
- Volume
- 52
- Issue
- -
- ISSN
- 1532-0480
- Open access status
- Out of scope for open access requirements
- Month of publication
- August
- Year of publication
- 2014
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
4
- Research group(s)
-
-
- Citation count
- 17
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- We show how to use meta-analysis results to parameterise a Bayesian network, contributing to the research theme of 'data and knowledge' for decision support modelling. The results of a meta-analysis are usually reported as univariate statistics (such as odds ratios), so that without the approach described here this information cannot be used in a probabilistic model. This research direction and partnership with the Centre for Trauma Science has led to recent funding including $1.2M from the DoD (see https://www.c4ts.qmul.ac.uk/modelling-and-prediction/combat-aid) to develop practical decision support tools for traumatic injury, in which the 'limb viability' model of this paper is one element.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -