ub.xmlui.mirage2.page-structure.muninLogoub.xmlui.mirage2.page-structure.openResearchArchiveLogo
    • EnglishEnglish
    • norsknorsk
  • Velg spraaknorsk 
    • EnglishEnglish
    • norsknorsk
  • Administrasjon/UB
Vis innførsel 
  •   Hjem
  • Det helsevitenskapelige fakultet
  • Institutt for klinisk medisin
  • Artikler, rapporter og annet (klinisk medisin)
  • Vis innførsel
  •   Hjem
  • Det helsevitenskapelige fakultet
  • Institutt for klinisk medisin
  • Artikler, rapporter og annet (klinisk medisin)
  • Vis innførsel
JavaScript is disabled for your browser. Some features of this site may not work without it.

Machine learning algorithms performed no better than regression models for prognostication in traumatic brain injury

Permanent lenke
https://hdl.handle.net/10037/20851
DOI
https://doi.org/10.1016/j.jclinepi.2020.03.005
Thumbnail
Åpne
article.pdf (551.9Kb)
Publisert versjon (PDF)
Dato
2020-03-19
Type
Journal article
Tidsskriftartikkel
Peer reviewed

Forfatter
Gravesteijn, BY; Nieboer, Daan; Ercole, Ari; Lingsma, Hester F; Nelson, David; Van Calster, Ben; Steyerberg, Ewout W; Andelic, Nada; Anke, Audny; Frisvold, Shirin; Helseth, Eirik; Røe, Cecilie; Røise, Olav; Skandsen, Toril; Vik, Anne
Sammendrag
Objective - 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.
Forlag
Elsevier
Sitering
Gravesteijn B, Nieboer D, Ercole A, Lingsma HF, Nelson D, Van Calster B, Steyerberg EW, Andelic N, Anke A, Frisvold S, Helseth E, Røe C, Røise O, Skandsen T, Vik A. Machine learning algorithms performed no better than regression models for prognostication in traumatic brain injury . Journal of Clinical Epidemiology. 2020
Metadata
Vis full innførsel
Samlinger
  • Artikler, rapporter og annet (klinisk medisin) [1974]
Copyright 2020 The Author(s)

Bla

Bla i hele MuninEnheter og samlingerForfatterlisteTittelDatoBla i denne samlingenForfatterlisteTittelDato
Logg inn

Statistikk

Antall visninger
UiT

Munin bygger på DSpace

UiT Norges Arktiske Universitet
Universitetsbiblioteket
uit.no/ub - munin@ub.uit.no

Tilgjengelighetserklæring