Forskning
Udskriv Udskriv
Switch language
Rigshospitalet - en del af Københavns Universitetshospital
Udgivet

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

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  1. A new tool to assess Clinical Diversity In Meta-analyses (CDIM) of interventions

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  2. Ecological momentary assessments (EMAs) did not improve responsiveness of patient-reported outcomes on quality of life

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  3. Consideration of confounding was suboptimal in the reporting of observational studies in psychiatry: a meta-epidemiological study

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  1. Questionnaires vs Interviews for the Assessment of Global Functional Outcomes After Traumatic Brain Injury

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  2. Nærdødsoplevelser

    Publikation: Bidrag til tidsskriftReviewForskningpeer review

  3. Occurrence and timing of withdrawal of life-sustaining measures in traumatic brain injury patients: a CENTER-TBI study

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  • Benjamin Y Gravesteijn
  • Daan Nieboer
  • Ari Ercole
  • Hester F Lingsma
  • David Nelson
  • Ben van Calster
  • Ewout W Steyerberg
  • CENTER-TBI collaborators
  • Daniel Kondziella (Medlem af forfattergruppering)
  • Martin Ejler Fabricius (Medlem af forfattergruppering)
Vis graf over relationer

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.

OriginalsprogEngelsk
TidsskriftJournal of Clinical Epidemiology
Vol/bind122
Sider (fra-til)95-107
Antal sider13
ISSN0895-4356
DOI
StatusUdgivet - jun. 2020

Bibliografisk note

Copyright © 2020 The Authors. Published by Elsevier Inc. All rights reserved.

ID: 61292571