Vis enkel innførsel

dc.contributor.authorGravesteijn, BY
dc.contributor.authorNieboer, Daan
dc.contributor.authorErcole, Ari
dc.contributor.authorLingsma, Hester F
dc.contributor.authorNelson, David
dc.contributor.authorVan Calster, Ben
dc.contributor.authorSteyerberg, Ewout W
dc.contributor.authorAndelic, Nada
dc.contributor.authorAnke, Audny
dc.contributor.authorFrisvold, Shirin
dc.contributor.authorHelseth, Eirik
dc.contributor.authorRøe, Cecilie
dc.contributor.authorRøise, Olav
dc.contributor.authorSkandsen, Toril
dc.contributor.authorVik, Anne
dc.date.accessioned2021-02-10T14:10:56Z
dc.date.available2021-02-10T14:10:56Z
dc.date.created2020-09-12T22:48:44Z
dc.date.issued2020
dc.identifier.issn0895-4356
dc.identifier.urihttps://hdl.handle.net/11250/2727247
dc.description.abstractObjective We aimed to explore the added value of common machine learning (ML) algorithms for prediction of outcome for moderate and severe traumatic brain injury. Study Design and Setting We performed logistic regression (LR), lasso regression, and ridge regression with key baseline predictors in the IMPACT-II database (15 studies, n = 11,022). ML algorithms included support vector machines, random forests, gradient boosting machines, and artificial neural networks and were trained using the same predictors. To assess generalizability of predictions, we performed internal, internal-external, and external validation on the recent CENTER-TBI study (patients with Glasgow Coma Scale <13, n = 1,554). Both calibration (calibration slope/intercept) and discrimination (area under the curve) was quantified. Results In the IMPACT-II database, 3,332/11,022 (30%) died and 5,233(48%) had unfavorable outcome (Glasgow Outcome Scale less than 4). In the CENTER-TBI study, 348/1,554(29%) died and 651(54%) had unfavorable outcome. Discrimination and calibration varied widely between the studies and less so between the studied algorithms. The mean area under the curve was 0.82 for mortality and 0.77 for unfavorable outcomes in the CENTER-TBI study. Conclusion ML algorithms may not outperform traditional regression approaches in a low-dimensional setting for outcome prediction after moderate or severe traumatic brain injury. Similar to regression-based prediction models, ML algorithms should be rigorously validated to ensure applicability to new populations.en_US
dc.language.isoengen_US
dc.publisherElsevieren_US
dc.rightsNavngivelse 4.0 Internasjonal*
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/deed.no*
dc.titleMachine learning algorithms performed no better than regression models for prognostication in traumatic brain injuryen_US
dc.typePeer revieweden_US
dc.typeJournal articleen_US
dc.description.versionpublishedVersionen_US
dc.source.journalJournal of Clinical Epidemiologyen_US
dc.identifier.doi10.1016/j.jclinepi.2020.03.005
dc.identifier.cristin1829378
dc.relation.projectEU/602150en_US
dc.relation.projectNorges forskningsråd: 272789en_US
dc.description.localcode/ 2020 The Authors. Published by Elsevier Inc. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/ 4.0/).en_US
cristin.ispublishedtrue
cristin.fulltextoriginal
cristin.qualitycode2


Tilhørende fil(er)

Thumbnail

Denne innførselen finnes i følgende samling(er)

Vis enkel innførsel

Navngivelse 4.0 Internasjonal
Med mindre annet er angitt, så er denne innførselen lisensiert som Navngivelse 4.0 Internasjonal