Mortality risk prediction in burn injury: Comparison of logistic regression with machine learning approaches
| Autor: | Neophytos Stylianou, Ken Dunn, Evangelos Kontopantelis, Artur Akbarov, Iain Buchan |
|---|---|
| Rok vydání: | 2015 |
| Předmět: |
Adult
Male Support Vector Machine Adolescent Body Surface Area Population Critical Care and Intensive Care Medicine Machine learning computer.software_genre Logistic regression Risk Assessment Logistic model tree Decision Support Techniques Machine Learning Young Adult Naive Bayes classifier Humans Medicine Registries Child education Multinomial logistic regression education.field_of_study Models Statistical Wales Receiver operating characteristic Artificial neural network business.industry Age Factors Infant Bayes Theorem General Medicine Smoke Inhalation Injury Random forest Logistic Models England ROC Curve Child Preschool Emergency Medicine Female Surgery Neural Networks Computer Artificial intelligence Burns business computer Software |
| Zdroj: | Burns. 41:925-934 |
| ISSN: | 0305-4179 |
| DOI: | 10.1016/j.burns.2015.03.016 |
| Popis: | 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 naive 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect