Random forest machine learning method outperforms prehospital National Early Warning Score for predicting one-day mortality : A retrospective study

Show simple item record

dc.contributor.author Pirneskoski, Jussi
dc.contributor.author Tamminen, Joonas
dc.contributor.author Kallonen, Antti
dc.contributor.author Nurmi, Jouni
dc.contributor.author Kuisma, Markku
dc.contributor.author Olkkola, Klaus T.
dc.contributor.author Hoppu, Sanna
dc.date.accessioned 2021-09-22T09:54:02Z
dc.date.available 2021-09-22T09:54:02Z
dc.date.issued 2020-12
dc.identifier.citation Pirneskoski , J , Tamminen , J , Kallonen , A , Nurmi , J , Kuisma , M , Olkkola , K T & Hoppu , S 2020 , ' Random forest machine learning method outperforms prehospital National Early Warning Score for predicting one-day mortality : A retrospective study ' , Resuscitation plus , vol. 4 , 100046 . https://doi.org/10.1016/j.resplu.2020.100046
dc.identifier.other PURE: 168668567
dc.identifier.other PURE UUID: d16829d2-367c-42ae-b4ee-8a51f642fc46
dc.identifier.other WOS: 000675511000019
dc.identifier.other ORCID: /0000-0002-3057-6524/work/100389953
dc.identifier.other ORCID: /0000-0001-7872-8665/work/100390530
dc.identifier.uri http://hdl.handle.net/10138/334541
dc.description.abstract Aim of the study: The National Early Warning Score (NEWS) is a validated method for predicting clinical deterioration in hospital wards, but its performance in prehospital settings remains controversial. Modern machine learning models may outperform traditional statistical analyses for predicting short-term mortality. Thus, we aimed to compare the mortality prediction accuracy of NEWS and random forest machine learning using prehospital vital signs. Methods: In this retrospective study, all electronic ambulance mission reports between 2008 and 2015 in a single EMS system were collected. Adult patients (>= 18 years) were included in the analysis. Random forest models with and without blood glucose were compared to the traditional NEWS for predicting one-day mortality. A ten-fold cross-validation method was applied to train and validate the random forest models. Results: A total of 26,458 patients were included in the study of whom 278 (1.0%) died within one day of ambulance mission. The area under the receiver operating characteristic curve for one-day mortality was 0.836 (95% CI, 0.810-0.860) for NEWS, 0.858 (95% CI, 0.832-0.883) for a random forest trained with NEWS variables only and 0.868 (0.843-0.892) for a random forest trained with NEWS variables and blood glucose. Conclusion: A random forest algorithm trained with NEWS variables was superior to traditional NEWS for predicting one-day mortality in adult prehospital patients, although the risk of selection bias must be acknowledged. The inclusion of blood glucose in the model further improved its predictive performance. en
dc.format.extent 7
dc.language.iso eng
dc.relation.ispartof Resuscitation plus
dc.rights cc_by
dc.rights.uri info:eu-repo/semantics/openAccess
dc.subject Emergency medical services
dc.subject Prehospital
dc.subject Cardiac arrest prevention
dc.subject Early warning score
dc.subject National Early Warning Score
dc.subject NEWS
dc.subject Random forest
dc.subject Machine learning
dc.subject IN-HOSPITAL MORTALITY
dc.subject CARE-UNIT ADMISSION
dc.subject RISK
dc.subject 3126 Surgery, anesthesiology, intensive care, radiology
dc.title Random forest machine learning method outperforms prehospital National Early Warning Score for predicting one-day mortality : A retrospective study en
dc.type Article
dc.contributor.organization Helsinki University Hospital Area
dc.contributor.organization HUS Emergency Medicine and Services
dc.contributor.organization Staff Services
dc.contributor.organization HUS Perioperative, Intensive Care and Pain Medicine
dc.contributor.organization Department of Diagnostics and Therapeutics
dc.contributor.organization Clinicum
dc.contributor.organization Anestesiologian yksikkö
dc.description.reviewstatus Peer reviewed
dc.relation.doi https://doi.org/10.1016/j.resplu.2020.100046
dc.relation.issn 2666-5204
dc.rights.accesslevel openAccess
dc.type.version publishedVersion

Files in this item

Total number of downloads: Loading...

Files Size Format View
1_s2.0_S2666520420300461_main.pdf 625.7Kb PDF View/Open

This item appears in the following Collection(s)

Show simple item record