Mortality risk prediction in burn injury: Comparison of logistic regression with machine learning approaches

Highlights • All prediction methods had comparable performances. • The established model performs well against more complex methods. • Methodologies of varying complexity should be used to monitor simple clinical prediction models.

Saved in:
Bibliographic Details
Published in:Burns 2015-08, Vol.41 (5), p.925-934
Main Authors: Stylianou, Neophytos, Akbarov, Artur, Kontopantelis, Evangelos, Buchan, Iain, Dunn, Ken W
Format: Article
Language:English
Subjects:
Adolescent
Adult
Age Factors
Bayes Theorem
Body Surface Area
Burn
Burns - mortality
Burns - pathology
Child
Child, Preschool
Clinical prediction
Critical Care
Decision Support Techniques
England
Female
Humans
Infant
Logistic Models
Machine Learning
Male
Models, Statistical
Mortality
Neural Networks, Computer
Registries
Risk Assessment - methods
ROC Curve
Smoke Inhalation Injury - mortality
Software
Support Vector Machine
Wales
Young Adult
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Highlights • All prediction methods had comparable performances. • The established model performs well against more complex methods. • Methodologies of varying complexity should be used to monitor simple clinical prediction models.
ISSN:0305-4179
1879-1409
DOI:10.1016/j.burns.2015.03.016