Skip to search boxSkip to navigationSkip to main content

Bayesian averaging over decision tree models: an application for estimating uncertainty in trauma severity scoring

  • University of Exeter
Research Output: Contribution to journal Article Peer-review

Open access

Abstract

Introduction For making reliable decisions, practitioners need to estimate uncertainties that exist in data and decision models. In this paper we analyse uncertainties of predicting survival probability for patients in trauma care. The existing prediction methodology employs logistic regression modelling of Trauma and Injury Severity Score(external)(external) (TRISS), which is based on theoretical assumptions. These assumptions limit the capability of TRISS methodology to provide accurate and reliable predictions. Methods We adopt the methodology of Bayesian model averaging and show how this methodology can be applied to decision trees in order to provide practitioners with new insights into the uncertainty. The proposed method has been validated on a large set of 447,176 cases registered in the US National Trauma Data Bank in terms of discrimination ability evaluated with receiver operating characteristic (ROC) and precision–recall (PRC) curves. Results Areas under curves were improved for ROC from 0.951 to 0.956 (p = 3.89 × 10−18) and for PRC from 0.564 to 0.605 (p = 3.89 × 10−18). The new model has significantly better calibration in terms of the Hosmer–Lemeshow Hˆ" role="presentation"> statistic, showing an improvement from 223.14 (the standard method) to 11.59 (p = 2.31 × 10−18). Conclusion The proposed Bayesian method is capable of improving the accuracy and reliability of survival prediction. The new method has been made available for evaluation purposes as a web application.

Publication Information

Output type

Research Output: Contribution to journal Article Peer-review

Original language

English

Pages from-to (Number of pages)

Pages 6-14

Journal (Volume, Issue Number)

International Journal of Medical Informatics (Volume 112)

Publication milestones

  • Published - 11/01/2018

Publication status

Published - 11/01/2018

ISSN

1386-5056

External Publication IDs

  • handle.net: 10547/622483
  • Scopus: 85041418850

Access to documents

Publication metrics

Metrics

Download statistics
Download count
4