PUBLICATION DATE

2015-08

TITLE

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

ISSUE

5

VOLUME

41

ISSN (print)

N/A

ISSN (electronic)

N/A

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. METHODS: An established logistic mortality model was compared to machine learning methods (artificial neural network, support vector machine, random forests and naïve Bayes) using a population-based (England & Wales) case-cohort registry. Predictive evaluation used: area under the receiver operating characteristic curve; sensitivity; specificity; positive predictive value and Youden's index. RESULTS: All methods had comparable discriminatory abilities, similar sensitivities, specificities and positive predictive values. Although some machine learning methods performed marginally better than logistic regression the differences were seldom statistically significant and clinically insubstantial. Random forests were marginally better for high positive predictive value and reasonable sensitivity. Neural networks yielded slightly better prediction overall. Logistic regression gives an optimal mix of performance and interpretability. DISCUSSION: The established logistic regression model of burn mortality performs well against more complex alternatives. Clinical prediction with a small set of strong, stable, independent predictors is unlikely to gain much from machine learning outside specialist research contexts.

Related objects

JOURNAL BRAND

N/A (note: articles not published by Springer Nature have limited metadata)


FROM GRANT

  • Mica: Health E-Research Centre
  • Health E-Research Centre -Herc
  • How to use: Click on a object to move its position. Double click to open its homepage. Right click to preview its contents.

    Download the RDF metadata as:   json-ld nt turtle xml License info


    15 TRIPLES      14 PREDICATES      16 URIs      10 LITERALS

    Subject Predicate Object
    1 articles:df96c25af86c234e8b507d12f0d107a9 sg: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. METHODS: An established logistic mortality model was compared to machine learning methods (artificial neural network, support vector machine, random forests and naïve Bayes) using a population-based (England & Wales) case-cohort registry. Predictive evaluation used: area under the receiver operating characteristic curve; sensitivity; specificity; positive predictive value and Youden's index. RESULTS: All methods had comparable discriminatory abilities, similar sensitivities, specificities and positive predictive values. Although some machine learning methods performed marginally better than logistic regression the differences were seldom statistically significant and clinically insubstantial. Random forests were marginally better for high positive predictive value and reasonable sensitivity. Neural networks yielded slightly better prediction overall. Logistic regression gives an optimal mix of performance and interpretability. DISCUSSION: The established logistic regression model of burn mortality performs well against more complex alternatives. Clinical prediction with a small set of strong, stable, independent predictors is unlikely to gain much from machine learning outside specialist research contexts.
    2 sg:doi 10.1016/j.burns.2015.03.016
    3 sg:doiLink http://dx.doi.org/10.1016/j.burns.2015.03.016
    4 sg:isFundedPublicationOf grants:067a1738e089873f68a349bbfeb46772
    5 grants:768c2514942b12f25c0e9b468bdb2c58
    6 sg:issue 5
    7 sg:language English
    8 sg:license http://scigraph.springernature.com/explorer/license/
    9 sg:publicationYear 2015
    10 sg:publicationYearMonth 2015-08
    11 sg:scigraphId df96c25af86c234e8b507d12f0d107a9
    12 sg:title Mortality risk prediction in burn injury: Comparison of logistic regression with machine learning approaches.
    13 sg:volume 41
    14 rdf:type sg:Article
    15 rdfs:label Article: Mortality risk prediction in burn injury: Comparison of logistic regression with machine learning approaches.
    HOW TO GET THIS DATA PROGRAMMATICALLY:

    JSON-LD is a popular JSON format for linked data.

    curl -H 'Accept: application/ld+json' 'http://scigraph.springernature.com/things/articles/df96c25af86c234e8b507d12f0d107a9'

    N-Triples is a line-based linked data format ideal for batch operations .

    curl -H 'Accept: application/n-triples' 'http://scigraph.springernature.com/things/articles/df96c25af86c234e8b507d12f0d107a9'

    Turtle is a human-readable linked data format.

    curl -H 'Accept: text/turtle' 'http://scigraph.springernature.com/things/articles/df96c25af86c234e8b507d12f0d107a9'

    RDF/XML is a standard XML format for linked data.

    curl -H 'Accept: application/rdf+xml' 'http://scigraph.springernature.com/things/articles/df96c25af86c234e8b507d12f0d107a9'






    Preview window. Press ESC to close (or click here)


    ...