Format

Send to

Choose Destination
J Clin Epidemiol. 2020 Mar 19. pii: S0895-4356(19)30875-3. doi: 10.1016/j.jclinepi.2020.03.005. [Epub ahead of print]

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

Collaborators (239)

Åkerlund C, Amrein K, Andelic N, Andreassen L, Anke A, Antoni A, Audibert G, Azouvi P, Azzolini ML, Bartels R, Barzó P, Beauvais R, Beer R, Bellander BM, Belli A, Benali H, Berardino M, Beretta L, Blaabjerg M, Bragge P, Brazinova A, Brinck V, Brooker J, Brorsson C, Buki A, Bullinger M, Cabeleira M, Caccioppola A, Calappi E, Calvi MR, Cameron P, Lozano GC, Carbonara M, Chevallard G, Chieregato A, Citerio G, Cnossen M, Coburn M, Coles J, Cooper DJ, Correia M, Čović A, Curry N, Czeiter E, Czosnyka M, Dahyot-Fizelier C, Dawes H, De Keyser V, Degos V, Della Corte F, Boogert HD, Depreitere B, Đilvesi Đ, Dixit A, Donoghue E, Guy-Loup Dulière JD, Ercole A, Esser P, Martin Fabricius EE, Feigin Kelly Foks VL, Frisvold S, Furmanov A, Gagliardo P, Galanaud D, Gantner D, Gao G, George P, Ghuysen A, Giga L, Glocker B, Golubovic J, Gomez PA, Gratz J, Gravesteijn B, Grossi F, Gruen RL, Gupta D, Haagsma JA, Haitsma I, Helbok R, Helseth E, Horton L, Huijben J, Hutchinson PJ, Jacobs B, Jankowski S, Ji-Yao Jiang MJ, Jones K, Karan M, Kolias AG, Kompanje E, Kondziella D, Koraropoulos E, Koskinen LO, Kovács N, Lagares A, Lanyon L, Laureys S, Lecky F, Lefering R, Legrand V, Lejeune A, Levi L, Lightfoot R, Lingsma H, Maas AIR, Castaño-León AM, Maegele M, Majdan M, Manara A, Manley G, Martino C, Maréchal H, Mattern J, McMahon C, Melegh B, Menon D, Menovsky T, Mulazzi D, Muraleedharan V, Murray L, Nair N, Negru A, Nelson D, Newcombe V, Nieboer D, Noirhomme Q, Nyirádi J, Olubukola O, Oresic M, Ortolano F, Palotie A, Parizel PM, Payen JF, Perera N, Perlbarg V, Persona P, Peul W, Piippo-Karjalainen A, Pirinen M, Ples H, Polinder S, Pomposo I, Posti JP, Puybasset L, Radoi A, Ragauskas A, Raj R, Rambadagalla M, Real R, Rhodes J, Richardson S, Richter S, Ripatti S, Rocka S, Roe C, Roise O, Rosand J, Rosenfeld JV, Rosenlund C, Rosenthal G, Rossaint R, Rossi S, Rueckert D, Rusnák M, Sahuquillo J, Sakowitz O, Sanchez-Porras R, Sandor J, Schäfer N, Schmidt S, Schoechl H, Schoonman G, Schou RF, Schwendenwein E, Sewalt C, Skandsen T, Smielewski P, Sorinola A, Stamatakis E, Stanworth S, Kowark A, Stevens R, Stewart W, Steyerberg EW, Stocchetti N, Sundström N, Synnot A, Takala R, Tamás V, Tamosuitis T, Taylor MS, Ao BT, Tenovuo O, Theadom A, Thomas M, Tibboel D, Timmers M, Tolias C, Trapani T, Tudora CM, Vajkoczy P, Vallance S, Valeinis E, Vámos Z, Van der Steen G, van der Naalt J, van Dijck JTJM, van Essen TA, Van Hecke W, van Heugten C, Van Praag D, Vyvere TV, Vanhaudenhuyse A, van Wijk RPJ, Vargiolu A, Vega E, Velt K, Verheyden J, Vespa PM, Vik A, Vilcinis R, Volovici V, von Steinbüchel N, Voormolen D, Vulekovic P, Wang KKW, Wiegers E, Williams G, Wilson L, Winzeck S, Wolf S, Yang Z, Ylén P, Younsi A, Zeiler FA, Zelinkova V, Ziverte A, Zoerle T.

Author information

1
Departments of Public Health, Erasmus MC - University Medical Centre Rotterdam, Postbus 2040 3000 CA, Rotterdam The Netherlands. Electronic address: b.gravesteijn@erasmusmc.nl.
2
Departments of Public Health, Erasmus MC - University Medical Centre Rotterdam, The Netherlands.
3
Division of Anaesthesia, University of Cambridge, United Kingdom.
4
Department of Physiology and Pharmacology, Section of Perioperative Medicine and Intensive Care, Karolinska Institutet, Stockholm, Sweden.
5
Department of Development and Regeneration, KU Leuven, Belgium; Department of Biomedical Data Sciences, Leiden university medical centre, Leiden, The Netherlands.
6
Department of Biomedical Data Sciences, Leiden university medical centre, Leiden, The Netherlands; Departments of Public Health, Erasmus MC - University Medical Centre Rotterdam, The Netherlands.

Abstract

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 (LR), lasso, 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 GCS<13, n = 1,554). Both calibration (calibration slope/intercept) and discrimination (AUC) was quantified.

RESULTS:

In the IMPACT-II database, 3,332/11,022(30%) died and 5,233(48%) had unfavorable outcome (Glasgow Outcome Scale below 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 AUC was 0.82 for mortality and 0.77 for unfavorable outcome in CENTER-TBI.

CONCLUSION:

ML algorithms may not outperform traditional regression approaches in a low-dimensional setting for outcome prediction after moderate or severe TBI. Similar to regression-based prediction models, ML algorithms should be rigorously validated to ensure applicability to new populations.

KEYWORDS:

Cohort study; Data science; Machine learning; Prediction; Prognosis; Traumatic brain injury

PMID:
32201256
DOI:
10.1016/j.jclinepi.2020.03.005
Free full text

Supplemental Content

Full text links

Icon for Elsevier Science
Loading ...
Support Center