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

Journal: Burns : journal of the International Society for Burn Injuries

PMID: 25931158

Abstract

INTRODUCTION: Predicting mortality from burn injury has traditionally employed logistic regression models. Alternative machine learning methods have been introduced in some areas of clinical prediction as the necessary software and computational facilities have become accessible. Here we compare logistic regression and machine learning predictions of mortality from burn.

Authors

Neophytos Stylianou

Centre for Health Informatics, Institute of Population Health, University of Manchester, UK. Electronic address: neophytos.stylianou@postgrad.manchester.ac.uk.
Artur Akbarov

Centre for Health Informatics, Institute of Population Health, University of Manchester, UK.
Evangelos Kontopantelis

Centre for Health Informatics, Institute of Population Health, University of Manchester, UK.
Iain Buchan

Centre for Health Informatics, Institute of Population Health, University of Manchester, UK.
Ken W Dunn

University Hospital South Manchester, Greater Manchester, UK.

Keywords

Adolescent Adult Age Factors Bayes Theorem Body Surface Area Burns Child Child, Preschool Decision Support Techniques England Female Humans Infant Logistic Models Machine Learning Male Models, Statistical Neural Networks, Computer Registries Risk Assessment ROC Curve Smoke Inhalation Injury Software Support Vector Machine Wales Young Adult

External Resources

View on PubMed Access via DOI PubMed (25931158)

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

Abstract

Authors

Keywords

External Resources

Popular Topics

Recent Journals