Predicting risk for adverse health events using random forest

Guy Cafri, Luo Li, Elizabeth W. Paxton and Juanjuan Fan

Journal of Applied Statistics, 2018, vol. 45, issue 12, 2279-2294

Abstract: Estimation of person-specific risk for adverse health events in medicine has been approached almost exclusively using parametric statistical methods. Random forest is a machine learning method based on tree ensembles that is completely nonparametric and for this reason may be better suited for risk prediction. An introduction to a random forest is provided with a focus on its application to risk prediction. Using data from a total joint replacement registry, we illustrate risk prediction for the binary outcome of 90-day mortality following implantation, as well as time to device failure for aseptic reasons with the competing risk of mortality. Using the methods described in this paper, the random forest could be applied to risk prediction in a wide variety of medical fields. Issues related to implementation are discussed.

Date: 2018
References: Add references at CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1080/02664763.2017.1414166 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:taf:japsta:v:45:y:2018:i:12:p:2279-2294

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/CJAS20

DOI: 10.1080/02664763.2017.1414166

Access Statistics for this article

Journal of Applied Statistics is currently edited by Robert Aykroyd

More articles in Journal of Applied Statistics from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().