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

We aimed to explore the added value of common machine learning (ML) algorithms for prediction of outcome for moderate and severe traumatic brain injury. We performed logistic regression (LR), lasso regression, and ridge regression with key baseline predictors in the IMPACT-II database (15 studies, n...

Full description

Saved in:
Bibliographic Details
Published inJournal of clinical epidemiology Vol. 122; no. 2; pp. 95 - 107
Main Authors Gravesteijn, Benjamin Y., Lingsma, Hester F., Nelson, David, Steyerberg, Ewout W., Andreassen, Lasse, Anke, Audny, Audibert, Gérard, Barzó, Pál, Beauvais, Romuald, Bellander, Bo-Michael, Benali, Habib, Beretta, Luigi, Blaabjerg, Morten, Brazinova, Alexandra, Brooker, Joanne, Brorsson, Camilla, Bullinger, Monika, Lozano, Guillermo Carbayo, Chieregato, Arturo, Coburn, Mark, Dawes, Helen, Della Corte, Francesco, Đilvesi, Đula, Esser, Patrick, Martin Fabricius, Erzsébet Ezer, Feigin, Kelly Foks, Valery L., Gagliardo, Pablo, Gantner, Dashiell, Gao, Guoyi, Glocker, Ben, Gravesteijn, Benjamin, Grossi, Francesca, Gruen, Russell L., Helbok, Raimund, Jacobs, Bram, Ji-yao Jiang, Mike Jarrett, Karan, Mladen, Kolias, Angelos G., Kompanje, Erwin, Koraropoulos, Evgenios, Koskinen, Lars-Owe, Laureys, Steven, Legrand, Valerie, Lightfoot, Roger, Lingsma, Hester, Castaño-León, Ana M., Manley, Geoffrey, Maréchal, Hugues, McMahon, Catherine, Menovsky, Tomas, Mulazzi, Davide, Nair, Nandesh, Nieboer, Daan, Nyirádi, József, Oresic, Matej, Ortolano, Fabrizio, Palotie, Aarno, Parizel, Paul M., Pirinen, Matti, Polinder, Suzanne, Posti, Jussi P., Puybasset, Louis, Radoi, Andreea, Rhodes, Jonathan, Richardson, Sylvia, Richter, Sophie, Ripatti, Samuli, Rocka, Saulius, Roe, Cecilie, Rosenlund, Christina, Rossaint, Rolf, Sakowitz, Oliver, Sandor, Janos, Schoechl, Herbert, Schou, Rico Frederik, Schwendenwein, Elisabeth, Sewalt, Charlie, Stamatakis, Emmanuel, Stanworth, Simon, Ao, Braden Te, Tenovuo, Olli, Theadom, Alice, Tibboel, Dick, Vajkoczy, Peter, Vallance, Shirley, van der Naalt, Joukje, van Dijck, Jeroen T.J.M., van Essen, Thomas A., van Heugten, Caroline, Van Praag, Dominique, Vyvere, Thijs Vande, Vespa, Paul M., Voormolen, Daphne, Wang, Kevin K.W., Wiegers, Eveline, Winzeck, Stefan, Wolf, Stefan, Yang, Zhihui, Younsi, Alexander, Zelinkova, Veronika
Format Journal Article
LanguageEnglish
Published United States Elsevier Inc 01.06.2020
Elsevier Limited
Elsevier
Elsevier USA
Subjects
Online AccessGet full text
ISSN0895-4356
1878-5921
1878-5921
DOI10.1016/j.jclinepi.2020.03.005

Cover

Abstract We aimed to explore the added value of common machine learning (ML) algorithms for prediction of outcome for moderate and severe traumatic brain injury. 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. 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. 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.
AbstractList 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. © 2020 The Authors
We aimed to explore the added value of common machine learning (ML) algorithms for prediction of outcome for moderate and severe traumatic brain injury. 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. 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. 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.
ObjectiveWe 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 SettingWe 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.ResultsIn 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.ConclusionML 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.
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&lt;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.
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.
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 &lt;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.
AbstractObjectiveWe 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 SettingWe 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. ResultsIn 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. ConclusionML 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.
We aimed to explore the added value of common machine learning (ML) algorithms for prediction of outcome for moderate and severe traumatic brain injury.OBJECTIVEWe aimed to explore the added value of common machine learning (ML) algorithms for prediction of outcome for moderate and severe traumatic brain injury.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.STUDY DESIGN AND SETTINGWe 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.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.RESULTSIn 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.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.CONCLUSIONML 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.
Author Tibboel, Dick
Esser, Patrick
Cabeleira, Manuel
Takala, Riikka
Jacobs, Bram
Rosenthal, Guy
Blaabjerg, Morten
Sakowitz, Oliver
Andreassen, Lasse
Bullinger, Monika
Martin Fabricius, Erzsébet Ezer
Laureys, Steven
Giga, Lelde
Majdan, Marek
Lingsma, Hester F.
Benali, Habib
Peul, Wilco
Valeinis, Egils
Smielewski, Peter
Vámos, Zoltán
Ghuysen, Alexandre
Kolias, Angelos G.
Perlbarg, Vincent
Thomas, Matt
Zeiler, Frederik A.
Rosand, Jonathan
Vajkoczy, Peter
Buki, Andras
Vallance, Shirley
Lightfoot, Roger
Feigin, Kelly Foks, Valery L.
Timmers, Marjolein
Schwendenwein, Elisabeth
Maréchal, Hugues
Huijben, Jilske
Kondziella, Daniel
Maas, Andrew I.R.
Beretta, Luigi
Coburn, Mark
Haitsma, Iain
Oresic, Matej
Ragauskas, Arminas
Trapani, Tony
Antoni, Anna
Velt, Kimberley
Sewalt, Charlie
Helbok, Raimund
Vanhaudenhuyse, Audrey
Steyerberg, Ewout W.
Gratz, Johannes
Synnot, Anneliese
Cameron, Peter
Karan, Mladen
Palotie, Aarno
Wilson, Lindsay
Czosnyka, Marek
Gomez, Pedro A.
Gravesteijn, Benjamin Y.
Zoerle, Tommaso
Lecky, Fiona
Tamosuitis, Tomas
Tolias, Christos
Golubovic,
Author_xml – sequence: 1
  givenname: Benjamin Y.
  surname: Gravesteijn
  fullname: Gravesteijn, Benjamin Y.
  email: b.gravesteijn@erasmusmc.nl
  organization: Departments of Public Health, Erasmus MC – University Medical Centre Rotterdam, Postbus 2040, 3000 CA, Rotterdam, the Netherlands
– sequence: 4
  givenname: Hester F.
  surname: Lingsma
  fullname: Lingsma, Hester F.
  organization: Departments of Public Health, Erasmus MC – University Medical Centre Rotterdam, Rotterdam, the Netherlands
– sequence: 5
  givenname: David
  surname: Nelson
  fullname: Nelson, David
  organization: Department of Physiology and Pharmacology, Section of Perioperative Medicine and Intensive Care, Karolinska Institutet, Stockholm, Sweden
– sequence: 7
  givenname: Ewout W.
  surname: Steyerberg
  fullname: Steyerberg, Ewout W.
  organization: Departments of Public Health, Erasmus MC – University Medical Centre Rotterdam, Rotterdam, the Netherlands
– sequence: 11
  givenname: Lasse
  surname: Andreassen
  fullname: Andreassen, Lasse
– sequence: 12
  givenname: Audny
  surname: Anke
  fullname: Anke, Audny
– sequence: 14
  givenname: Gérard
  surname: Audibert
  fullname: Audibert, Gérard
– sequence: 18
  givenname: Pál
  surname: Barzó
  fullname: Barzó, Pál
– sequence: 19
  givenname: Romuald
  surname: Beauvais
  fullname: Beauvais, Romuald
– sequence: 21
  givenname: Bo-Michael
  surname: Bellander
  fullname: Bellander, Bo-Michael
– sequence: 23
  givenname: Habib
  surname: Benali
  fullname: Benali, Habib
– sequence: 25
  givenname: Luigi
  surname: Beretta
  fullname: Beretta, Luigi
– sequence: 26
  givenname: Morten
  surname: Blaabjerg
  fullname: Blaabjerg, Morten
– sequence: 28
  givenname: Alexandra
  surname: Brazinova
  fullname: Brazinova, Alexandra
– sequence: 30
  givenname: Joanne
  surname: Brooker
  fullname: Brooker, Joanne
– sequence: 31
  givenname: Camilla
  surname: Brorsson
  fullname: Brorsson, Camilla
– sequence: 33
  givenname: Monika
  surname: Bullinger
  fullname: Bullinger, Monika
– sequence: 39
  givenname: Guillermo Carbayo
  surname: Lozano
  fullname: Lozano, Guillermo Carbayo
– sequence: 42
  givenname: Arturo
  surname: Chieregato
  fullname: Chieregato, Arturo
– sequence: 45
  givenname: Mark
  surname: Coburn
  fullname: Coburn, Mark
– sequence: 54
  givenname: Helen
  surname: Dawes
  fullname: Dawes, Helen
– sequence: 57
  givenname: Francesco
  surname: Della Corte
  fullname: Della Corte, Francesco
– sequence: 60
  givenname: Đula
  surname: Đilvesi
  fullname: Đilvesi, Đula
– sequence: 65
  givenname: Patrick
  surname: Esser
  fullname: Esser, Patrick
– sequence: 66
  givenname: Erzsébet Ezer
  surname: Martin Fabricius
  fullname: Martin Fabricius, Erzsébet Ezer
– sequence: 67
  givenname: Valery L.
  surname: Feigin, Kelly Foks
  fullname: Feigin, Kelly Foks, Valery L.
– sequence: 70
  givenname: Pablo
  surname: Gagliardo
  fullname: Gagliardo, Pablo
– sequence: 72
  givenname: Dashiell
  surname: Gantner
  fullname: Gantner, Dashiell
– sequence: 73
  givenname: Guoyi
  surname: Gao
  fullname: Gao, Guoyi
– sequence: 77
  givenname: Ben
  surname: Glocker
  fullname: Glocker, Ben
– sequence: 81
  givenname: Benjamin
  surname: Gravesteijn
  fullname: Gravesteijn, Benjamin
– sequence: 82
  givenname: Francesca
  surname: Grossi
  fullname: Grossi, Francesca
– sequence: 83
  givenname: Russell L.
  surname: Gruen
  fullname: Gruen, Russell L.
– sequence: 87
  givenname: Raimund
  surname: Helbok
  fullname: Helbok, Raimund
– sequence: 92
  givenname: Bram
  surname: Jacobs
  fullname: Jacobs, Bram
– sequence: 94
  givenname: Mike Jarrett
  surname: Ji-yao Jiang
  fullname: Ji-yao Jiang, Mike Jarrett
– sequence: 96
  givenname: Mladen
  surname: Karan
  fullname: Karan, Mladen
– sequence: 97
  givenname: Angelos G.
  surname: Kolias
  fullname: Kolias, Angelos G.
– sequence: 98
  givenname: Erwin
  surname: Kompanje
  fullname: Kompanje, Erwin
– sequence: 100
  givenname: Evgenios
  surname: Koraropoulos
  fullname: Koraropoulos, Evgenios
– sequence: 101
  givenname: Lars-Owe
  surname: Koskinen
  fullname: Koskinen, Lars-Owe
– sequence: 105
  givenname: Steven
  surname: Laureys
  fullname: Laureys, Steven
– sequence: 108
  givenname: Valerie
  surname: Legrand
  fullname: Legrand, Valerie
– sequence: 111
  givenname: Roger
  surname: Lightfoot
  fullname: Lightfoot, Roger
– sequence: 112
  givenname: Hester
  surname: Lingsma
  fullname: Lingsma, Hester
– sequence: 114
  givenname: Ana M.
  surname: Castaño-León
  fullname: Castaño-León, Ana M.
– sequence: 118
  givenname: Geoffrey
  surname: Manley
  fullname: Manley, Geoffrey
– sequence: 120
  givenname: Hugues
  surname: Maréchal
  fullname: Maréchal, Hugues
– sequence: 122
  givenname: Catherine
  surname: McMahon
  fullname: McMahon, Catherine
– sequence: 125
  givenname: Tomas
  surname: Menovsky
  fullname: Menovsky, Tomas
– sequence: 126
  givenname: Davide
  surname: Mulazzi
  fullname: Mulazzi, Davide
– sequence: 129
  givenname: Nandesh
  surname: Nair
  fullname: Nair, Nandesh
– sequence: 133
  givenname: Daan
  surname: Nieboer
  fullname: Nieboer, Daan
– sequence: 135
  givenname: József
  surname: Nyirádi
  fullname: Nyirádi, József
– sequence: 137
  givenname: Matej
  surname: Oresic
  fullname: Oresic, Matej
– sequence: 138
  givenname: Fabrizio
  surname: Ortolano
  fullname: Ortolano, Fabrizio
– sequence: 139
  givenname: Aarno
  surname: Palotie
  fullname: Palotie, Aarno
– sequence: 140
  givenname: Paul M.
  surname: Parizel
  fullname: Parizel, Paul M.
– sequence: 147
  givenname: Matti
  surname: Pirinen
  fullname: Pirinen, Matti
– sequence: 149
  givenname: Suzanne
  surname: Polinder
  fullname: Polinder, Suzanne
– sequence: 151
  givenname: Jussi P.
  surname: Posti
  fullname: Posti, Jussi P.
– sequence: 152
  givenname: Louis
  surname: Puybasset
  fullname: Puybasset, Louis
– sequence: 153
  givenname: Andreea
  surname: Radoi
  fullname: Radoi, Andreea
– sequence: 158
  givenname: Jonathan
  surname: Rhodes
  fullname: Rhodes, Jonathan
– sequence: 159
  givenname: Sylvia
  surname: Richardson
  fullname: Richardson, Sylvia
– sequence: 160
  givenname: Sophie
  surname: Richter
  fullname: Richter, Sophie
– sequence: 161
  givenname: Samuli
  surname: Ripatti
  fullname: Ripatti, Samuli
– sequence: 162
  givenname: Saulius
  surname: Rocka
  fullname: Rocka, Saulius
– sequence: 163
  givenname: Cecilie
  surname: Roe
  fullname: Roe, Cecilie
– sequence: 167
  givenname: Christina
  surname: Rosenlund
  fullname: Rosenlund, Christina
– sequence: 169
  givenname: Rolf
  surname: Rossaint
  fullname: Rossaint, Rolf
– sequence: 174
  givenname: Oliver
  surname: Sakowitz
  fullname: Sakowitz, Oliver
– sequence: 176
  givenname: Janos
  surname: Sandor
  fullname: Sandor, Janos
– sequence: 179
  givenname: Herbert
  surname: Schoechl
  fullname: Schoechl, Herbert
– sequence: 181
  givenname: Rico Frederik
  surname: Schou
  fullname: Schou, Rico Frederik
– sequence: 182
  givenname: Elisabeth
  surname: Schwendenwein
  fullname: Schwendenwein, Elisabeth
– sequence: 183
  givenname: Charlie
  surname: Sewalt
  fullname: Sewalt, Charlie
– sequence: 187
  givenname: Emmanuel
  surname: Stamatakis
  fullname: Stamatakis, Emmanuel
– sequence: 188
  givenname: Simon
  surname: Stanworth
  fullname: Stanworth, Simon
– sequence: 200
  givenname: Braden Te
  surname: Ao
  fullname: Ao, Braden Te
– sequence: 201
  givenname: Olli
  surname: Tenovuo
  fullname: Tenovuo, Olli
– sequence: 202
  givenname: Alice
  surname: Theadom
  fullname: Theadom, Alice
– sequence: 204
  givenname: Dick
  surname: Tibboel
  fullname: Tibboel, Dick
– sequence: 209
  givenname: Peter
  surname: Vajkoczy
  fullname: Vajkoczy, Peter
– sequence: 210
  givenname: Shirley
  surname: Vallance
  fullname: Vallance, Shirley
– sequence: 214
  givenname: Joukje
  surname: van der Naalt
  fullname: van der Naalt, Joukje
– sequence: 215
  givenname: Jeroen T.J.M.
  surname: van Dijck
  fullname: van Dijck, Jeroen T.J.M.
– sequence: 216
  givenname: Thomas A.
  surname: van Essen
  fullname: van Essen, Thomas A.
– sequence: 218
  givenname: Caroline
  surname: van Heugten
  fullname: van Heugten, Caroline
– sequence: 219
  givenname: Dominique
  surname: Van Praag
  fullname: Van Praag, Dominique
– sequence: 220
  givenname: Thijs Vande
  surname: Vyvere
  fullname: Vyvere, Thijs Vande
– sequence: 227
  givenname: Paul M.
  surname: Vespa
  fullname: Vespa, Paul M.
– sequence: 232
  givenname: Daphne
  surname: Voormolen
  fullname: Voormolen, Daphne
– sequence: 234
  givenname: Kevin K.W.
  surname: Wang
  fullname: Wang, Kevin K.W.
– sequence: 235
  givenname: Eveline
  surname: Wiegers
  fullname: Wiegers, Eveline
– sequence: 238
  givenname: Stefan
  surname: Winzeck
  fullname: Winzeck, Stefan
– sequence: 239
  givenname: Stefan
  surname: Wolf
  fullname: Wolf, Stefan
– sequence: 240
  givenname: Zhihui
  surname: Yang
  fullname: Yang, Zhihui
– sequence: 242
  givenname: Alexander
  surname: Younsi
  fullname: Younsi, Alexander
– sequence: 244
  givenname: Veronika
  surname: Zelinkova
  fullname: Zelinkova, Veronika
BackLink https://www.ncbi.nlm.nih.gov/pubmed/32201256$$D View this record in MEDLINE/PubMed
https://hal.science/hal-04831821$$DView record in HAL
https://urn.kb.se/resolve?urn=urn:nbn:se:oru:diva-81118$$DView record from Swedish Publication Index
https://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-171371$$DView record from Swedish Publication Index
http://kipublications.ki.se/Default.aspx?queryparsed=id:143918942$$DView record from Swedish Publication Index
BookMark eNqNk9tq3DAQhk1JaQ7tK6SG3rTQ3epg2TKU0iU9pJDSix5uB1me9WqjlbaSnbBvXzlOAs1FEhBYGn3_ePhndJjtOe8wy44pmVNCy3fr-Vpb43Br5owwMid8Toh4kh1QWcmZqBndyw6IrMWs4KLczw5jXBNCK1KJZ9k-Z4xQJsqDrP-u9CrlyS2q4IzrcmU7H0y_2sR8i2Hpwwbb3Pm8wb7HkPcr5fKAXcAYjXf5xrdoY564fBt853zsjVb9eGVc3gc1bNJJ501QZgyth7B7nj1dKhvxxfX3KPv95fOvk9PZ2Y-v304WZzNdlXU_K0RLlk3dNKRoaKkpZVKUbVpVKxRrSdtg2cq6IG0hCeFcaFkKUSjZlrKolyU_yqop7-C2aneprIVtMBsVdkAJjD7CGm58hNFHIBySj0k5m5TxErdDcyvzysB16DztEIqKiaq4l_9k_izAhw6GzQC0ojyto-ztw7wPA0hKqUw4n3BrsMN00Ri4YFf01X6wHSgNDQJjpQRW1JzxpHozqVbK_veH08UZjDFSSE4loxdjQS8nVgeTOujA-aCSRYRXyRgpRuL1RKQ2_x0w9rAxUaO1yqEfIjAuabJdiNG9V3fQtR-CS61OpaWxS-2qR8-Or6mhSTN2W-HNcCbg_U1NPsaAS9CmvxqtNFbGPtzD8o780c3_OAnTYOOFwQBRG3QaWxNQ99B683CKD3dSjFR6GPYcdxhv7aAQGRD4Ob7U8aHSmhNZCX5_gsdU8A-yNk-o
CitedBy_id crossref_primary_10_1038_s41598_023_28421_6
crossref_primary_10_1371_journal_pone_0270973
crossref_primary_10_1016_j_annemergmed_2022_05_011
crossref_primary_10_1016_j_compbiomed_2024_109634
crossref_primary_10_3389_fneur_2023_1288740
crossref_primary_10_3390_healthcare11192687
crossref_primary_10_1016_j_jclinepi_2021_07_015
crossref_primary_10_1038_s42003_023_05588_2
crossref_primary_10_3390_s22249861
crossref_primary_10_1016_j_wneu_2021_01_002
crossref_primary_10_1007_s11910_025_01405_x
crossref_primary_10_1038_s41598_025_89574_0
crossref_primary_10_1007_s12028_021_01260_x
crossref_primary_10_1161_STROKEAHA_120_033445
crossref_primary_10_3390_nu14091705
crossref_primary_10_53841_bpsneur_2024_1_17_21
crossref_primary_10_2196_46840
crossref_primary_10_1016_j_crad_2024_08_015
crossref_primary_10_3171_2021_8_FOCUS2155
crossref_primary_10_4103_jfsm_jfsm_35_24
crossref_primary_10_3390_app112110126
crossref_primary_10_1007_s11282_024_00792_0
crossref_primary_10_3389_fneur_2021_729184
crossref_primary_10_2147_DNND_S435806
crossref_primary_10_1001_jamanetworkopen_2023_55024
crossref_primary_10_3390_diagnostics13091640
crossref_primary_10_2147_DMSO_S316950
crossref_primary_10_1038_s41416_024_02693_9
crossref_primary_10_1038_s41591_022_01961_6
crossref_primary_10_1177_11795468221133611
crossref_primary_10_1007_s00586_022_07188_w
crossref_primary_10_1016_j_imu_2022_100984
crossref_primary_10_1016_j_ijmedinf_2021_104496
crossref_primary_10_1186_s12874_024_02319_x
crossref_primary_10_1002_wps_20882
crossref_primary_10_1186_s12874_021_01469_6
crossref_primary_10_1007_s11517_022_02752_4
crossref_primary_10_1016_j_compbiomed_2024_109372
crossref_primary_10_1016_j_ibmed_2023_100118
crossref_primary_10_1089_neu_2022_0280
crossref_primary_10_59717_j_xinn_med_2024_100105
crossref_primary_10_1007_s00134_021_06583_z
crossref_primary_10_3390_brainsci12091232
crossref_primary_10_3390_bios12121176
crossref_primary_10_3389_fneur_2025_1512297
crossref_primary_10_1016_j_wneu_2022_06_130
crossref_primary_10_1186_s13037_024_00403_1
crossref_primary_10_3389_fnins_2022_1099560
crossref_primary_10_1111_anae_16315
crossref_primary_10_1016_j_enbuild_2022_111870
crossref_primary_10_1016_j_trgeo_2022_100756
crossref_primary_10_1186_s12874_021_01347_1
crossref_primary_10_3390_biomedicines10102472
crossref_primary_10_1371_journal_pone_0317819
crossref_primary_10_1038_s41598_023_28188_w
crossref_primary_10_1200_CCI_21_00077
crossref_primary_10_2196_50895
crossref_primary_10_3389_fmed_2021_810195
crossref_primary_10_1371_journal_pdig_0000642
crossref_primary_10_1097_j_pain_0000000000003023
crossref_primary_10_1016_j_wneu_2024_05_065
crossref_primary_10_1016_j_surg_2023_03_012
crossref_primary_10_1038_s41598_022_22566_6
crossref_primary_10_1089_neu_2022_0221
crossref_primary_10_1177_0310057X211030927
crossref_primary_10_3390_ani10091687
crossref_primary_10_1212_CON_0000000000001433
crossref_primary_10_1016_j_wneu_2022_02_097
crossref_primary_10_1158_1055_9965_EPI_22_0677
crossref_primary_10_1177_14604582231164694
crossref_primary_10_2196_58740
crossref_primary_10_1371_journal_pone_0280173
crossref_primary_10_1186_s12911_022_01953_z
crossref_primary_10_1111_exsy_70005
crossref_primary_10_3390_biomedicines10092267
crossref_primary_10_1007_s00521_023_08258_w
crossref_primary_10_1016_j_compbiomed_2022_105458
crossref_primary_10_1093_neuros_nyab337
crossref_primary_10_1007_s00167_022_07181_2
crossref_primary_10_1016_j_chemolab_2024_105064
crossref_primary_10_1016_j_est_2022_104903
crossref_primary_10_1016_j_cjtee_2021_06_003
crossref_primary_10_2147_DMSO_S288881
crossref_primary_10_1007_s13755_021_00138_8
crossref_primary_10_1016_j_jclinepi_2020_12_018
crossref_primary_10_1016_j_resuscitation_2022_04_028
crossref_primary_10_1038_s41598_022_21390_2
crossref_primary_10_4103_ijnpnd_ijnpnd_93_20
crossref_primary_10_1016_j_jdent_2024_104921
crossref_primary_10_1089_neu_2022_0365
crossref_primary_10_1016_j_wneu_2022_04_044
crossref_primary_10_3389_fneur_2021_666875
crossref_primary_10_1080_02699052_2022_2034184
crossref_primary_10_1016_j_gsf_2023_101647
crossref_primary_10_3390_min15040330
crossref_primary_10_1007_s10916_022_01809_z
crossref_primary_10_1089_neu_2022_0515
crossref_primary_10_1186_s12874_021_01493_6
crossref_primary_10_1111_jdi_14256
crossref_primary_10_1007_s11906_024_01297_1
crossref_primary_10_3390_biomedicines10030686
crossref_primary_10_2147_RMHP_S328180
crossref_primary_10_1007_s00595_023_02662_4
crossref_primary_10_1186_s12911_023_02247_8
crossref_primary_10_1139_apnm_2021_0448
crossref_primary_10_3171_2021_10_JNS211261
crossref_primary_10_1002_uog_27515
crossref_primary_10_3389_fnut_2022_740898
crossref_primary_10_1186_s12874_021_01265_2
crossref_primary_10_1186_s12877_021_02392_7
crossref_primary_10_1027_1015_5759_a000714
crossref_primary_10_1136_bmjopen_2021_055918
crossref_primary_10_3389_fneur_2022_859068
crossref_primary_10_1089_neu_2023_0467
crossref_primary_10_1371_journal_pone_0309175
crossref_primary_10_1016_j_ijmedinf_2023_105201
crossref_primary_10_25259_SNI_312_2023
crossref_primary_10_2139_ssrn_4076679
crossref_primary_10_1016_S0140_6736_21_00038_6
crossref_primary_10_1038_s41598_022_24909_9
crossref_primary_10_1097_WCO_0000000000000875
Cites_doi 10.1186/s12911-017-0566-6
10.1016/S1474-4422(10)70065-X
10.1038/s41746-018-0029-1
10.1089/neu.2006.0036
10.1186/s12911-018-0659-x
10.1371/journal.pmed.1002368
10.1016/S1470-2045(19)30149-4
10.1016/0197-2456(86)90046-2
10.3389/fneur.2018.00784
10.1093/biomet/80.1.27
10.1089/neu.2008.0586
10.1371/journal.pone.0207192
10.1023/A:1009715923555
10.1016/S2468-2667(16)30017-2
10.1186/s12859-018-2344-6
10.1002/cem.2790
10.3389/fnbot.2013.00021
10.1097/CCM.0000000000001571
10.1097/CCM.0000000000003011
10.1111/j.2517-6161.1996.tb02080.x
10.1038/nn.3818
10.1371/journal.pmed.0050165
10.1002/sim.1691
10.1136/bmjopen-2017-017199
10.1016/j.jclinepi.2015.04.005
10.7326/M14-0697
10.1093/eurheartj/ehu207
10.1016/j.jclinepi.2016.03.002
10.1186/s12911-015-0206-y
10.1016/j.jclinepi.2015.12.005
10.1093/jamia/ocy032
10.1097/EDE.0b013e3181c30fb2
10.1016/j.jcrc.2019.08.010
10.2307/2531595
10.1001/jama.2017.18391
10.1186/1471-2288-14-137
10.1093/biomet/45.3-4.562
10.1023/A:1010933404324
10.1136/heartjnl-2011-301247
10.1016/S1474-4422(17)30371-X
10.3390/jcm7110428
10.1002/sim.3069
10.1097/SHK.0000000000000898
10.1016/j.jclinepi.2019.02.004
10.1089/neu.2018.6276
10.1016/S1474-4422(12)70166-7
10.1227/NEU.0000000000000575
ContentType Journal Article
Contributor Esser, Patrick
Cabeleira, Manuel
Ji-Yao Jiang, Mike Jarrett
Jacobs, Bram
Blaabjerg, Morten
Gravesteijn, Benjamin
Andreassen, Lasse
Bullinger, Monika
Martin Fabricius, Erzsébet Ezer
Andelic, Nada
Laureys, Steven
Giga, Lelde
Benali, Habib
Kolias, Angelos G
Guy-Loup Dulière, Jens Dreier
Ghuysen, Alexandre
Calappi, Emiliana
Anke, Audny
Buki, Andras
Ercole, Ari
Huijben, Jilske
Kondziella, Daniel
Kovács, Noémi
Azouvi, Philippe
Brooker, Joanne
Beretta, Luigi
Coburn, Mark
Haitsma, Iain
Frisvold, Shirin
Dawes, Helen
Haagsma, Juanita A
Antoni, Anna
Đilvesi, Đula
Amrein, Krisztina
Helbok, Raimund
Gratz, Johannes
Cameron, Peter
Karan, Mladen
Czosnyka, Marek
Coles, Jonathan
Koskinen, Lars-Owe
Lecky, Fiona
Beauvais, Romuald
Caccioppola, Alessio
Azzolini, Maria Luisa
Dahyot-Fizelier, Claire
Golubovic, Jagoš
Grossi, Francesca
Brazinova, Alexandra
Čović, Amra
Furmanov, Alex
Carbonara, Marco
Gao, Guoyi
Dixit, Abhishek
Gantner, Dashiell
Barzó, Pál
Horton, Lindsay
Donoghue, Emma
Belli, Antonio
Brorsson, Camilla
Hutchinson, Peter J
Czeiter, Endre
Depreitere, Bart
Cnos
CHU de Liège-Centre du Cerveau² - ULiège
Oresic, Matej
Contributor_xml – sequence: 1
  givenname: Cecilia
  surname: Åkerlund
  fullname: Åkerlund, Cecilia
– sequence: 1
  fullname: CHU de Liège-Centre du Cerveau² - ULiège
– sequence: 1
  givenname: Matej
  surname: Oresic
  fullname: Oresic, Matej
  organization: The CENTER-TBI collaborators
– sequence: 1
  givenname: Camilla
  surname: Brorsson
  fullname: Brorsson, Camilla
  organization: Anestesiologi och intensivvård
– sequence: 2
  givenname: Krisztina
  surname: Amrein
  fullname: Amrein, Krisztina
– sequence: 3
  givenname: Nada
  surname: Andelic
  fullname: Andelic, Nada
– sequence: 4
  givenname: Lasse
  surname: Andreassen
  fullname: Andreassen, Lasse
– sequence: 5
  givenname: Audny
  surname: Anke
  fullname: Anke, Audny
– sequence: 6
  givenname: Anna
  surname: Antoni
  fullname: Antoni, Anna
– sequence: 7
  givenname: Gérard
  surname: Audibert
  fullname: Audibert, Gérard
– sequence: 8
  givenname: Philippe
  surname: Azouvi
  fullname: Azouvi, Philippe
– sequence: 9
  givenname: Maria Luisa
  surname: Azzolini
  fullname: Azzolini, Maria Luisa
– sequence: 10
  givenname: Ronald
  surname: Bartels
  fullname: Bartels, Ronald
– sequence: 11
  givenname: Pál
  surname: Barzó
  fullname: Barzó, Pál
– sequence: 12
  givenname: Romuald
  surname: Beauvais
  fullname: Beauvais, Romuald
– sequence: 13
  givenname: Ronny
  surname: Beer
  fullname: Beer, Ronny
– sequence: 14
  givenname: Bo-Michael
  surname: Bellander
  fullname: Bellander, Bo-Michael
– sequence: 15
  givenname: Antonio
  surname: Belli
  fullname: Belli, Antonio
– sequence: 16
  givenname: Habib
  surname: Benali
  fullname: Benali, Habib
– sequence: 17
  givenname: Maurizio
  surname: Berardino
  fullname: Berardino, Maurizio
– sequence: 18
  givenname: Luigi
  surname: Beretta
  fullname: Beretta, Luigi
– sequence: 19
  givenname: Morten
  surname: Blaabjerg
  fullname: Blaabjerg, Morten
– sequence: 20
  givenname: Peter
  surname: Bragge
  fullname: Bragge, Peter
– sequence: 21
  givenname: Alexandra
  surname: Brazinova
  fullname: Brazinova, Alexandra
– sequence: 22
  givenname: Vibeke
  surname: Brinck
  fullname: Brinck, Vibeke
– sequence: 23
  givenname: Joanne
  surname: Brooker
  fullname: Brooker, Joanne
– sequence: 24
  givenname: Camilla
  surname: Brorsson
  fullname: Brorsson, Camilla
– sequence: 25
  givenname: Andras
  surname: Buki
  fullname: Buki, Andras
– sequence: 26
  givenname: Monika
  surname: Bullinger
  fullname: Bullinger, Monika
– sequence: 27
  givenname: Manuel
  surname: Cabeleira
  fullname: Cabeleira, Manuel
– sequence: 28
  givenname: Alessio
  surname: Caccioppola
  fullname: Caccioppola, Alessio
– sequence: 29
  givenname: Emiliana
  surname: Calappi
  fullname: Calappi, Emiliana
– sequence: 30
  givenname: Maria Rosa
  surname: Calvi
  fullname: Calvi, Maria Rosa
– sequence: 31
  givenname: Peter
  surname: Cameron
  fullname: Cameron, Peter
– sequence: 32
  givenname: Guillermo Carbayo
  surname: Lozano
  fullname: Lozano, Guillermo Carbayo
– sequence: 33
  givenname: Marco
  surname: Carbonara
  fullname: Carbonara, Marco
– sequence: 34
  givenname: Giorgio
  surname: Chevallard
  fullname: Chevallard, Giorgio
– sequence: 35
  givenname: Arturo
  surname: Chieregato
  fullname: Chieregato, Arturo
– sequence: 36
  givenname: Giuseppe
  surname: Citerio
  fullname: Citerio, Giuseppe
– sequence: 37
  givenname: Maryse
  surname: Cnossen
  fullname: Cnossen, Maryse
– sequence: 38
  givenname: Mark
  surname: Coburn
  fullname: Coburn, Mark
– sequence: 39
  givenname: Jonathan
  surname: Coles
  fullname: Coles, Jonathan
– sequence: 40
  givenname: D Jamie
  surname: Cooper
  fullname: Cooper, D Jamie
– sequence: 41
  givenname: Marta
  surname: Correia
  fullname: Correia, Marta
– sequence: 42
  givenname: Amra
  surname: Čović
  fullname: Čović, Amra
– sequence: 43
  givenname: Nicola
  surname: Curry
  fullname: Curry, Nicola
– sequence: 44
  givenname: Endre
  surname: Czeiter
  fullname: Czeiter, Endre
– sequence: 45
  givenname: Marek
  surname: Czosnyka
  fullname: Czosnyka, Marek
– sequence: 46
  givenname: Claire
  surname: Dahyot-Fizelier
  fullname: Dahyot-Fizelier, Claire
– sequence: 47
  givenname: Helen
  surname: Dawes
  fullname: Dawes, Helen
– sequence: 48
  givenname: Véronique
  surname: De Keyser
  fullname: De Keyser, Véronique
– sequence: 49
  givenname: Vincent
  surname: Degos
  fullname: Degos, Vincent
– sequence: 50
  givenname: Francesco
  surname: Della Corte
  fullname: Della Corte, Francesco
– sequence: 51
  givenname: Hugo den
  surname: Boogert
  fullname: Boogert, Hugo den
– sequence: 52
  givenname: Bart
  surname: Depreitere
  fullname: Depreitere, Bart
– sequence: 53
  givenname: Đula
  surname: Đilvesi
  fullname: Đilvesi, Đula
– sequence: 54
  givenname: Abhishek
  surname: Dixit
  fullname: Dixit, Abhishek
– sequence: 55
  givenname: Emma
  surname: Donoghue
  fullname: Donoghue, Emma
– sequence: 56
  givenname: Jens Dreier
  surname: Guy-Loup Dulière
  fullname: Guy-Loup Dulière, Jens Dreier
– sequence: 57
  givenname: Ari
  surname: Ercole
  fullname: Ercole, Ari
– sequence: 58
  givenname: Patrick
  surname: Esser
  fullname: Esser, Patrick
– sequence: 59
  givenname: Erzsébet Ezer
  surname: Martin Fabricius
  fullname: Martin Fabricius, Erzsébet Ezer
– sequence: 60
  givenname: Valery L
  surname: Feigin Kelly Foks
  fullname: Feigin Kelly Foks, Valery L
– sequence: 61
  givenname: Shirin
  surname: Frisvold
  fullname: Frisvold, Shirin
– sequence: 62
  givenname: Alex
  surname: Furmanov
  fullname: Furmanov, Alex
– sequence: 63
  givenname: Pablo
  surname: Gagliardo
  fullname: Gagliardo, Pablo
– sequence: 64
  givenname: Damien
  surname: Galanaud
  fullname: Galanaud, Damien
– sequence: 65
  givenname: Dashiell
  surname: Gantner
  fullname: Gantner, Dashiell
– sequence: 66
  givenname: Guoyi
  surname: Gao
  fullname: Gao, Guoyi
– sequence: 67
  givenname: Pradeep
  surname: George
  fullname: George, Pradeep
– sequence: 68
  givenname: Alexandre
  surname: Ghuysen
  fullname: Ghuysen, Alexandre
– sequence: 69
  givenname: Lelde
  surname: Giga
  fullname: Giga, Lelde
– sequence: 70
  givenname: Ben
  surname: Glocker
  fullname: Glocker, Ben
– sequence: 71
  givenname: Jagoš
  surname: Golubovic
  fullname: Golubovic, Jagoš
– sequence: 72
  givenname: Pedro A
  surname: Gomez
  fullname: Gomez, Pedro A
– sequence: 73
  givenname: Johannes
  surname: Gratz
  fullname: Gratz, Johannes
– sequence: 74
  givenname: Benjamin
  surname: Gravesteijn
  fullname: Gravesteijn, Benjamin
– sequence: 75
  givenname: Francesca
  surname: Grossi
  fullname: Grossi, Francesca
– sequence: 76
  givenname: Russell L
  surname: Gruen
  fullname: Gruen, Russell L
– sequence: 77
  givenname: Deepak
  surname: Gupta
  fullname: Gupta, Deepak
– sequence: 78
  givenname: Juanita A
  surname: Haagsma
  fullname: Haagsma, Juanita A
– sequence: 79
  givenname: Iain
  surname: Haitsma
  fullname: Haitsma, Iain
– sequence: 80
  givenname: Raimund
  surname: Helbok
  fullname: Helbok, Raimund
– sequence: 81
  givenname: Eirik
  surname: Helseth
  fullname: Helseth, Eirik
– sequence: 82
  givenname: Lindsay
  surname: Horton
  fullname: Horton, Lindsay
– sequence: 83
  givenname: Jilske
  surname: Huijben
  fullname: Huijben, Jilske
– sequence: 84
  givenname: Peter J
  surname: Hutchinson
  fullname: Hutchinson, Peter J
– sequence: 85
  givenname: Bram
  surname: Jacobs
  fullname: Jacobs, Bram
– sequence: 86
  givenname: Stefan
  surname: Jankowski
  fullname: Jankowski, Stefan
– sequence: 87
  givenname: Mike Jarrett
  surname: Ji-Yao Jiang
  fullname: Ji-Yao Jiang, Mike Jarrett
– sequence: 88
  givenname: Kelly
  surname: Jones
  fullname: Jones, Kelly
– sequence: 89
  givenname: Mladen
  surname: Karan
  fullname: Karan, Mladen
– sequence: 90
  givenname: Angelos G
  surname: Kolias
  fullname: Kolias, Angelos G
– sequence: 91
  givenname: Erwin
  surname: Kompanje
  fullname: Kompanje, Erwin
– sequence: 92
  givenname: Daniel
  surname: Kondziella
  fullname: Kondziella, Daniel
– sequence: 93
  givenname: Evgenios
  surname: Koraropoulos
  fullname: Koraropoulos, Evgenios
– sequence: 94
  givenname: Lars-Owe
  surname: Koskinen
  fullname: Koskinen, Lars-Owe
– sequence: 95
  givenname: Noémi
  surname: Kovács
  fullname: Kovács, Noémi
– sequence: 96
  givenname: Alfonso
  surname: Lagares
  fullname: Lagares, Alfonso
– sequence: 97
  givenname: Linda
  surname: Lanyon
  fullname: Lanyon, Linda
– sequence: 98
  givenname: Steven
  surname: Laureys
  fullname: Laureys, Steven
– sequence: 99
  givenname: Fiona
  surname: Lecky
  fullname: Lecky, Fiona
– sequence: 100
  givenname: Rolf
  surname: Lefering
  fullname: Lefering, Rolf
Copyright 2020 The Authors
The Authors
Copyright © 2020 The Authors. Published by Elsevier Inc. All rights reserved.
2020. The Authors
info:eu-repo/semantics/openAccess
Distributed under a Creative Commons Attribution 4.0 International License
Copyright_xml – notice: 2020 The Authors
– notice: The Authors
– notice: Copyright © 2020 The Authors. Published by Elsevier Inc. All rights reserved.
– notice: 2020. The Authors
– notice: info:eu-repo/semantics/openAccess
– notice: Distributed under a Creative Commons Attribution 4.0 International License
CorporateAuthor CENTER-TBI collaborators
CorporateAuthor_xml – name: CENTER-TBI collaborators
DBID 6I.
AAFTH
AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
3V.
7QL
7QP
7RV
7T2
7T7
7TK
7U7
7U9
7X7
7XB
88C
88E
8AO
8C1
8FD
8FI
8FJ
8FK
8G5
ABUWG
AEUYN
AFKRA
AZQEC
BENPR
C1K
CCPQU
DWQXO
FR3
FYUFA
GHDGH
GNUQQ
GUQSH
H94
K9.
KB0
M0S
M0T
M1P
M2O
M7N
MBDVC
NAPCQ
P64
PHGZM
PHGZT
PJZUB
PKEHL
PPXIY
PQEST
PQQKQ
PQUKI
Q9U
7X8
3HK
1XC
JLOSS
Q33
AABEP
ADTPV
AOWAS
D8T
D91
ZZAVC
ADHXS
D93
ADTOC
UNPAY
DOI 10.1016/j.jclinepi.2020.03.005
DatabaseName ScienceDirect Open Access Titles
Elsevier:ScienceDirect:Open Access
CrossRef
Medline
MEDLINE
MEDLINE (Ovid)
MEDLINE
MEDLINE
PubMed
ProQuest Central (Corporate)
Bacteriology Abstracts (Microbiology B)
Calcium & Calcified Tissue Abstracts
Nursing & Allied Health Database
Health and Safety Science Abstracts (Full archive)
Industrial and Applied Microbiology Abstracts (Microbiology A)
Neurosciences Abstracts
Toxicology Abstracts
Virology and AIDS Abstracts
Health & Medical Collection
ProQuest Central (purchase pre-March 2016)
Healthcare Administration Database (Alumni)
Medical Database (Alumni Edition)
ProQuest Pharma Collection
Public Health Database
Technology Research Database
Hospital Premium Collection
Hospital Premium Collection (Alumni Edition)
ProQuest Central (Alumni) (purchase pre-March 2016)
ProQuest Research Library
ProQuest Central (Alumni)
ProQuest One Sustainability
ProQuest Central UK/Ireland
ProQuest Central Essentials
ProQuest Central
Environmental Sciences and Pollution Management
ProQuest One
ProQuest Central Korea
Engineering Research Database
Proquest Health Research Premium Collection
Health Research Premium Collection (Alumni)
ProQuest Central Student
ProQuest Research Library
AIDS and Cancer Research Abstracts
ProQuest Health & Medical Complete (Alumni)
Nursing & Allied Health Database (Alumni Edition)
ProQuest Health & Medical Collection
Healthcare Administration Database
Medical Database
Research Library
Algology Mycology and Protozoology Abstracts (Microbiology C)
Research Library (Corporate)
Nursing & Allied Health Premium
Biotechnology and BioEngineering Abstracts
ProQuest Central Premium
ProQuest One Academic
ProQuest Health & Medical Research Collection
ProQuest One Academic Middle East (New)
ProQuest One Health & Nursing
ProQuest One Academic Eastern Edition (DO NOT USE)
ProQuest One Academic
ProQuest One Academic UKI Edition
ProQuest Central Basic
MEDLINE - Academic
NORA - Norwegian Open Research Archives
Hyper Article en Ligne (HAL)
Université de Liège - Open Repository and Bibliography (ORBI) (Open Access titles only)
Université de Liège - Open Repository and Bibliography (ORBI)
SWEPUB Örebro universitet full text
SwePub
SwePub Articles
SWEPUB Freely available online
SWEPUB Örebro universitet
SwePub Articles full text
SWEPUB Umeå universitet full text
SWEPUB Umeå universitet
Unpaywall for CDI: Periodical Content
Unpaywall
DatabaseTitle CrossRef
MEDLINE
Medline Complete
MEDLINE with Full Text
PubMed
MEDLINE (Ovid)
Research Library Prep
ProQuest Central Student
ProQuest Central Essentials
Environmental Sciences and Pollution Management
ProQuest One Sustainability
Health Research Premium Collection
Health & Medical Research Collection
Industrial and Applied Microbiology Abstracts (Microbiology A)
ProQuest Central (New)
ProQuest Medical Library (Alumni)
Virology and AIDS Abstracts
ProQuest One Academic Eastern Edition
ProQuest Hospital Collection
Health Research Premium Collection (Alumni)
Neurosciences Abstracts
ProQuest Hospital Collection (Alumni)
Biotechnology and BioEngineering Abstracts
Nursing & Allied Health Premium
ProQuest Health & Medical Complete
ProQuest One Academic UKI Edition
ProQuest Health Management (Alumni Edition)
ProQuest Nursing & Allied Health Source (Alumni)
Engineering Research Database
ProQuest One Academic
Calcium & Calcified Tissue Abstracts
ProQuest One Academic (New)
Technology Research Database
ProQuest One Academic Middle East (New)
ProQuest Health & Medical Complete (Alumni)
ProQuest Central (Alumni Edition)
ProQuest One Community College
ProQuest One Health & Nursing
Research Library (Alumni Edition)
ProQuest Pharma Collection
ProQuest Central
ProQuest Health & Medical Research Collection
Health and Medicine Complete (Alumni Edition)
ProQuest Central Korea
Bacteriology Abstracts (Microbiology B)
Algology Mycology and Protozoology Abstracts (Microbiology C)
AIDS and Cancer Research Abstracts
ProQuest Research Library
Health & Safety Science Abstracts
ProQuest Public Health
ProQuest Central Basic
Toxicology Abstracts
ProQuest Health Management
ProQuest Nursing & Allied Health Source
ProQuest Medical Library
ProQuest Central (Alumni)
MEDLINE - Academic
DatabaseTitleList
MEDLINE
Research Library Prep






MEDLINE - Academic
Database_xml – sequence: 1
  dbid: NPM
  name: PubMed
  url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
  sourceTypes: Index Database
– sequence: 2
  dbid: EIF
  name: MEDLINE
  url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search
  sourceTypes: Index Database
– sequence: 3
  dbid: UNPAY
  name: Unpaywall
  url: https://proxy.k.utb.cz/login?url=https://unpaywall.org/
  sourceTypes: Open Access Repository
– sequence: 4
  dbid: BENPR
  name: ProQuest Central
  url: http://www.proquest.com/pqcentral?accountid=15518
  sourceTypes: Aggregation Database
DeliveryMethod fulltext_linktorsrc
Discipline Medicine
EISSN 1878-5921
EndPage 107
ExternalDocumentID 10.1016/j.jclinepi.2020.03.005
oai_swepub_ki_se_472574
oai_DiVA_org_umu_171371
oai_DiVA_org_oru_81118
oai_orbi_ulg_ac_be_2268_249323
oai:HAL:hal-04831821v1
10037_20851
32201256
10_1016_j_jclinepi_2020_03_005
S0895435619308753
1_s2_0_S0895435619308753
Genre Research Support, Non-U.S. Gov't
Journal Article
Comparative Study
GroupedDBID ---
--K
--M
-~X
.1-
.55
.FO
.GJ
.~1
0R~
1B1
1P~
1RT
1~.
1~5
29K
4.4
457
4CK
4G.
53G
5GY
5RE
5VS
7-5
71M
7RV
7X7
88E
8AO
8C1
8FI
8FJ
8G5
8P~
9JM
9JO
AABNK
AAEDT
AAEDW
AAFJI
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AATTM
AAWTL
AAXKI
AAXUO
AAYJJ
AAYWO
ABBQC
ABFNM
ABIVO
ABJNI
ABLJU
ABMAC
ABMMH
ABMZM
ABOCM
ABUWG
ABWVN
ABXDB
ACDAQ
ACGFS
ACIEU
ACIUM
ACLOT
ACPRK
ACRLP
ACRPL
ACVFH
ADBBV
ADCNI
ADEZE
ADMUD
ADNMO
AEBSH
AEIPS
AEKER
AENEX
AEUPX
AEUYN
AEVXI
AFFNX
AFJKZ
AFKRA
AFPUW
AFRAH
AFRHN
AFTJW
AFXIZ
AGHFR
AGQPQ
AGUBO
AGYEJ
AHHHB
AHMBA
AIEXJ
AIGII
AIIUN
AIKHN
AITUG
AJRQY
AJUYK
AKBMS
AKRWK
AKYEP
ALMA_UNASSIGNED_HOLDINGS
AMRAJ
ANKPU
ANZVX
AOMHK
APXCP
AQUVI
ASPBG
AVARZ
AVWKF
AXJTR
AZFZN
AZQEC
BENPR
BKEYQ
BKOJK
BLXMC
BNPGV
BPHCQ
BVXVI
CCPQU
CS3
D-I
DU5
DWQXO
EBS
EFJIC
EFKBS
EFLBG
EJD
EMOBN
EO8
EO9
EP2
EP3
EX3
F5P
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
FYUFA
G-2
G-Q
GBLVA
GNUQQ
GUQSH
HEH
HMCUK
HMK
HMO
HVGLF
HZ~
IHE
J1W
KOM
L7B
M0T
M1P
M29
M2O
M3W
M41
MO0
N9A
NAPCQ
O-L
O9-
OAUVE
OD~
OHT
OO0
OZT
P-8
P-9
P2P
PC.
PHGZM
PHGZT
PJZUB
PPXIY
PQQKQ
PRBVW
PROAC
PSQYO
Q38
R2-
ROL
RPZ
SAE
SCC
SDF
SDG
SDP
SEL
SES
SEW
SPCBC
SSB
SSH
SSO
SSZ
SV3
T5K
UAP
UKHRP
WOW
WUQ
X7M
XPP
YHZ
Z5R
ZGI
~G-
~HD
3V.
AACTN
AFCTW
AFKWA
AJOXV
ALIPV
AMFUW
RIG
6I.
AAFTH
AAIAV
ABLVK
ABYKQ
AHPSJ
AJBFU
AKYCK
F3I
LCYCR
ZA5
AAYXX
CITATION
CGR
CUY
CVF
ECM
EIF
NPM
7QL
7QP
7T2
7T7
7TK
7U7
7U9
7XB
8FD
8FK
C1K
FR3
H94
K9.
M7N
MBDVC
P64
PKEHL
PQEST
PQUKI
Q9U
7X8
PUEGO
08R
3HK
AALMO
AAUGY
ABPIF
ABPTK
1XC
JLOSS
Q33
AABEP
ADTPV
AGCQF
AOWAS
D8T
D91
ZZAVC
ADHXS
D93
ADTOC
AFFHD
UNPAY
ID FETCH-LOGICAL-c769t-45d0fb9bb04b16c112856d56d7d5a2d0dbe6d8940d4800335c86554a8d6849f63
IEDL.DBID .~1
ISSN 0895-4356
1878-5921
IngestDate Thu Oct 30 06:00:45 EDT 2025
Mon Oct 20 03:25:08 EDT 2025
Tue Sep 09 23:41:16 EDT 2025
Tue Sep 09 23:20:00 EDT 2025
Sat Oct 18 19:23:33 EDT 2025
Tue Oct 14 20:44:11 EDT 2025
Sat Apr 29 05:43:11 EDT 2023
Sun Sep 28 00:10:52 EDT 2025
Tue Oct 07 05:40:31 EDT 2025
Wed Feb 19 02:30:30 EST 2025
Thu Oct 16 04:47:11 EDT 2025
Thu Apr 24 23:05:25 EDT 2025
Fri Feb 23 02:47:53 EST 2024
Tue Feb 25 20:07:18 EST 2025
Tue Oct 14 19:36:04 EDT 2025
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 2
Keywords Data science
Prognosis
Traumatic brain injury
Cohort study
Machine learning
Prediction
NN
LR
Gradient boosting machine
Glasgow coma scale
SVM
Support vector machine
Neural network
Random Forest
Logistic regression
GBM
RF
GCS
TBI
ML
Language English
License This is an open access article under the CC BY license.
Copyright © 2020 The Authors. Published by Elsevier Inc. All rights reserved.
Distributed under a Creative Commons Attribution 4.0 International License: http://creativecommons.org/licenses/by/4.0
other-oa
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c769t-45d0fb9bb04b16c112856d56d7d5a2d0dbe6d8940d4800335c86554a8d6849f63
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ObjectType-Article-2
ObjectType-Feature-1
content type line 23
Journal of Clinical Epidemiology
scopus-id:2-s2.0-85082847791
ORCID 0000-0002-6849-1825
0000-0002-6540-5725
0000-0001-7158-1218
0000-0002-3096-3807
0000-0002-4288-9237
OpenAccessLink https://www.sciencedirect.com/science/article/pii/S0895435619308753
PMID 32201256
PQID 2425648094
PQPubID 105585
PageCount 13
ParticipantIDs unpaywall_primary_10_1016_j_jclinepi_2020_03_005
swepub_primary_oai_swepub_ki_se_472574
swepub_primary_oai_DiVA_org_umu_171371
swepub_primary_oai_DiVA_org_oru_81118
liege_orbi_v2_oai_orbi_ulg_ac_be_2268_249323
hal_primary_oai_HAL_hal_04831821v1
cristin_nora_10037_20851
proquest_miscellaneous_2381849555
proquest_journals_2425648094
pubmed_primary_32201256
crossref_citationtrail_10_1016_j_jclinepi_2020_03_005
crossref_primary_10_1016_j_jclinepi_2020_03_005
elsevier_sciencedirect_doi_10_1016_j_jclinepi_2020_03_005
elsevier_clinicalkeyesjournals_1_s2_0_S0895435619308753
elsevier_clinicalkey_doi_10_1016_j_jclinepi_2020_03_005
PublicationCentury 2000
PublicationDate 2020-06-01
PublicationDateYYYYMMDD 2020-06-01
PublicationDate_xml – month: 06
  year: 2020
  text: 2020-06-01
  day: 01
PublicationDecade 2020
PublicationPlace United States
PublicationPlace_xml – name: United States
– name: Elmsford
PublicationTitle Journal of clinical epidemiology
PublicationTitleAlternate J Clin Epidemiol
PublicationYear 2020
Publisher Elsevier Inc
Elsevier Limited
Elsevier
Elsevier USA
Publisher_xml – name: Elsevier Inc
– name: Elsevier Limited
– name: Elsevier
– name: Elsevier USA
References Burges (bib6) 1998; 2
Buuren (bib32) 2018
Collins, Reitsma, Altman, Moons (bib23) 2015; 162
Steyerberg, Harrell (bib34) 2016; 69
Bisaso, Karungi, Kiragga, Mukonzo, Castelnuovo (bib18) 2018; 18
Steyerberg, Vergouwe (bib39) 2014; 35
Decruyenaere, Decruyenaere, Peeters, Vermassen, Dhaene, Couckuyt (bib19) 2015; 15
Christodoulou, Jie, Collins, Steyerberg, Verbakel, van Calster (bib14) 2019; 110
Van Calster, Nieboer, Vergouwe, De Cock, Pencina, Steyerberg (bib22) 2016; 74
Delahanty, Kaufman, Jones (bib52) 2018; 46
Probst, Boulesteix, Bischl (bib41) 2019; 20
Marmarou, Lu, Butcher, McHugh, Mushkudiani, Murray (bib26) 2007; 24
van der Ploeg, Austin, Steyerberg (bib13) 2014; 14
FIRTH (bib30) 1993; 80
Cox (bib35) 1958; 45
Beam, Kohane (bib51) 2018; 319
Breiman (bib40) 2001; 45
Rau, Kuo, Chien, Huang, Hsieh, Hsieh (bib10) 2018; 13
Steyerberg, Vickers, Cook, Gerds, Gonen, Obuchowski (bib37) 2010; 21
van der Ploeg, Nieboer, Steyerberg (bib46) 2016; 78
van Os HJA, Ramos, Hilbert, van Leeuwen, van Walderveen, Kruyt (bib15) 2018; 9
Reps, Schuemie, Suchard, Ryan, Rijnbeek (bib55) 2018; 25
König, Malley, Weimar, Diener, Ziegler (bib43) 2007; 26
Thelin, Nelson, Vehvilä Inen, Nyströ, Kivisaari, Siironen (bib44) 2017; 14
Klau, Jurinovic, Hornung, Herold, Boulesteix (bib54) 2018; 19
Desautels, Das, Calvert, Trivedi, Summers, Wales (bib53) 2017; 7
Liu, Salinas (bib5) 2017; 48
Saatman, Duhaime, Bullock, Maas, Valadka, Manley (bib3) 2008; 25
Steyerberg, Mushkudiani, Perel, Butcher, Lu, McHugh (bib25) 2008; 5
Matsuo, Aihara, Nakai, Morishita, Tohma, Kohmura (bib11) 2018; 37
Afanador, Smolinska, Tran, Blanchet (bib8) 2016; 30
Lingsma, Roozenbeek, Steyerberg, Murray, Maas (bib4) 2010; 9
Charles, Gabriel, Searcy (bib49) 2016; 35
Maas, Menon, Adelson, Andelic, Bell, Belli (bib1) 2017; 16
Harrell (bib20) 2001
Rajkomar, Oren, Chen, Dai, Hajaj, Hardt (bib50) 2018; 1
Natekin, Knoll (bib9) 2013; 7
Neurology (bib48) 2012; 11
Rubin (bib31) 2004
Sakr, Elshawi, Ahmed, Qureshi, Brawner, Keteyian (bib42) 2017; 17
Jain, Mao, Mohiuddin (bib7) 1996; 29
DeLong, DeLong, Clarke-Pearson (bib36) 1988; 44
Steyerberg (bib28) 2009
Steyerberg (bib21) 2009
Moons, Kengne, Grobbee, Royston, Vergouwe, Altman (bib24) 2012; 98
Maas, Menon, Steyerberg, Citerio, Lecky, Manley (bib27) 2015; 76
Lee, Yoon, Yang, Kim, Ryu, Jung (bib17) 2018; 7
Majdan, Plancikova, Brazinova, Rusnak, Nieboer, Feigin (bib2) 2016; 1
Feng, Wang, Peng, Sun, Zeng, Jiang (bib12) 2019; 54
Churpek, Yuen, Winslow, Meltzer, Kattan, Edelson (bib16) 2016; 44
Royston, Parmar, Sylvester (bib33) 2004; 23
Poldrack, Gorgolewski (bib47) 2014; 17
Ngiam, Khor (bib45) 2019; 20
DerSimonian, Laird (bib38) 1986; 7
Tibshirani (bib29) 1996; 58
Feng (10.1016/j.jclinepi.2020.03.005_bib12) 2019; 54
Afanador (10.1016/j.jclinepi.2020.03.005_bib8) 2016; 30
Steyerberg (10.1016/j.jclinepi.2020.03.005_bib37) 2010; 21
Steyerberg (10.1016/j.jclinepi.2020.03.005_bib34) 2016; 69
Probst (10.1016/j.jclinepi.2020.03.005_bib41) 2019; 20
Lee (10.1016/j.jclinepi.2020.03.005_bib17) 2018; 7
van Os HJA (10.1016/j.jclinepi.2020.03.005_bib15) 2018; 9
Maas (10.1016/j.jclinepi.2020.03.005_bib27) 2015; 76
Steyerberg (10.1016/j.jclinepi.2020.03.005_bib39) 2014; 35
Delahanty (10.1016/j.jclinepi.2020.03.005_bib52) 2018; 46
Rajkomar (10.1016/j.jclinepi.2020.03.005_bib50) 2018; 1
Poldrack (10.1016/j.jclinepi.2020.03.005_bib47) 2014; 17
Moons (10.1016/j.jclinepi.2020.03.005_bib24) 2012; 98
Burges (10.1016/j.jclinepi.2020.03.005_bib6) 1998; 2
Van Calster (10.1016/j.jclinepi.2020.03.005_bib22) 2016; 74
Decruyenaere (10.1016/j.jclinepi.2020.03.005_bib19) 2015; 15
van der Ploeg (10.1016/j.jclinepi.2020.03.005_bib13) 2014; 14
Liu (10.1016/j.jclinepi.2020.03.005_bib5) 2017; 48
van der Ploeg (10.1016/j.jclinepi.2020.03.005_bib46) 2016; 78
Harrell (10.1016/j.jclinepi.2020.03.005_bib20) 2001
DerSimonian (10.1016/j.jclinepi.2020.03.005_bib38) 1986; 7
Jain (10.1016/j.jclinepi.2020.03.005_bib7) 1996; 29
Sakr (10.1016/j.jclinepi.2020.03.005_bib42) 2017; 17
Majdan (10.1016/j.jclinepi.2020.03.005_bib2) 2016; 1
Rubin (10.1016/j.jclinepi.2020.03.005_bib31) 2004
Lingsma (10.1016/j.jclinepi.2020.03.005_bib4) 2010; 9
Ngiam (10.1016/j.jclinepi.2020.03.005_bib45) 2019; 20
Charles (10.1016/j.jclinepi.2020.03.005_bib49) 2016; 35
Churpek (10.1016/j.jclinepi.2020.03.005_bib16) 2016; 44
Marmarou (10.1016/j.jclinepi.2020.03.005_bib26) 2007; 24
Desautels (10.1016/j.jclinepi.2020.03.005_bib53) 2017; 7
Royston (10.1016/j.jclinepi.2020.03.005_bib33) 2004; 23
Neurology (10.1016/j.jclinepi.2020.03.005_bib48) 2012; 11
DeLong (10.1016/j.jclinepi.2020.03.005_bib36) 1988; 44
Maas (10.1016/j.jclinepi.2020.03.005_bib1) 2017; 16
Buuren (10.1016/j.jclinepi.2020.03.005_bib32) 2018
Beam (10.1016/j.jclinepi.2020.03.005_bib51) 2018; 319
Matsuo (10.1016/j.jclinepi.2020.03.005_bib11) 2018; 37
Bisaso (10.1016/j.jclinepi.2020.03.005_bib18) 2018; 18
König (10.1016/j.jclinepi.2020.03.005_bib43) 2007; 26
Rau (10.1016/j.jclinepi.2020.03.005_bib10) 2018; 13
Steyerberg (10.1016/j.jclinepi.2020.03.005_bib21) 2009
Thelin (10.1016/j.jclinepi.2020.03.005_bib44) 2017; 14
Reps (10.1016/j.jclinepi.2020.03.005_bib55) 2018; 25
Saatman (10.1016/j.jclinepi.2020.03.005_bib3) 2008; 25
Cox (10.1016/j.jclinepi.2020.03.005_bib35) 1958; 45
Tibshirani (10.1016/j.jclinepi.2020.03.005_bib29) 1996; 58
FIRTH (10.1016/j.jclinepi.2020.03.005_bib30) 1993; 80
Natekin (10.1016/j.jclinepi.2020.03.005_bib9) 2013; 7
Collins (10.1016/j.jclinepi.2020.03.005_bib23) 2015; 162
Steyerberg (10.1016/j.jclinepi.2020.03.005_bib25) 2008; 5
Breiman (10.1016/j.jclinepi.2020.03.005_bib40) 2001; 45
Steyerberg (10.1016/j.jclinepi.2020.03.005_bib28) 2009
Klau (10.1016/j.jclinepi.2020.03.005_bib54) 2018; 19
Christodoulou (10.1016/j.jclinepi.2020.03.005_bib14) 2019; 110
References_xml – volume: 14
  start-page: 137
  year: 2014
  ident: bib13
  article-title: Modern modelling techniques are data hungry: a simulation study for predicting dichotomous endpoints
  publication-title: BMC Med Res Methodol
– volume: 54
  start-page: 110
  year: 2019
  end-page: 116
  ident: bib12
  article-title: Comparison between logistic regression and machine learning algorithms on survival prediction of traumatic brain injuries
  publication-title: J Crit Care
– volume: 98
  start-page: 691
  year: 2012
  end-page: 698
  ident: bib24
  article-title: Risk prediction models: II. External validation, model updating, and impact assessment
  publication-title: Heart
– volume: 21
  start-page: 128
  year: 2010
  end-page: 138
  ident: bib37
  article-title: Assessing the performance of prediction models: a framework for traditional and novel measures
  publication-title: Epidemiology
– volume: 11
  start-page: 651
  year: 2012
  ident: bib48
  article-title: The changing landscape of traumatic brain injury research
  publication-title: Lancet Neurol
– volume: 1
  start-page: e76
  year: 2016
  end-page: e83
  ident: bib2
  article-title: Epidemiology of traumatic brain injuries in Europe: a cross-sectional analysis
  publication-title: Lancet Public Heal
– volume: 7
  start-page: e017199
  year: 2017
  ident: bib53
  article-title: Prediction of early unplanned intensive care unit readmission in a UK tertiary care hospital: a cross-sectional machine learning approach
  publication-title: BMJ Open
– volume: 45
  start-page: 5
  year: 2001
  end-page: 32
  ident: bib40
  article-title: Random Forests
  publication-title: Mach Learn
– volume: 25
  start-page: 969
  year: 2018
  end-page: 975
  ident: bib55
  article-title: Design and implementation of a standardized framework to generate and evaluate patient-level prediction models using observational healthcare data
  publication-title: J Am Med Inform Assoc
– volume: 26
  start-page: 5499
  year: 2007
  end-page: 5511
  ident: bib43
  article-title: Practical experiences on the necessity of external validation
  publication-title: Stat Med
– volume: 2
  start-page: 121
  year: 1998
  end-page: 167
  ident: bib6
  article-title: A tutorial on support vector machines for pattern recognition
  publication-title: Data Mining Knowledge Discovery
– volume: 18
  start-page: 77
  year: 2018
  ident: bib18
  article-title: A comparative study of logistic regression based machine learning techniques for prediction of early virological suppression in antiretroviral initiating HIV patients
  publication-title: BMC Med Inform Decis Mak
– volume: 319
  start-page: 1317
  year: 2018
  ident: bib51
  article-title: Big data and machine learning in health care
  publication-title: JAMA
– year: 2001
  ident: bib20
  article-title: Regression Modeling Strategies
– year: 2009
  ident: bib21
  article-title: Clinical Prediction Models
– volume: 78
  start-page: 83
  year: 2016
  end-page: 89
  ident: bib46
  article-title: Modern modeling techniques had limited external validity in predicting mortality from traumatic brain injury
  publication-title: J Clin Epidemiol
– volume: 25
  start-page: 719
  year: 2008
  end-page: 738
  ident: bib3
  article-title: Classification of traumatic brain injury for targeted therapies
  publication-title: J Neurotrauma
– volume: 9
  start-page: 543
  year: 2010
  end-page: 554
  ident: bib4
  article-title: Early prognosis in traumatic brain injury: from prophecies to predictions
  publication-title: Lancet Neurol
– volume: 5
  start-page: e165
  year: 2008
  ident: bib25
  article-title: Predicting outcome after traumatic brain injury: development and international validation of prognostic scores based on admission characteristics
  publication-title: PLoS Med
– volume: 35
  start-page: 1
  year: 2016
  end-page: 9
  ident: bib49
  article-title: Adoption of electronic health record systems among U.S. non-federal acute care hospitals: 2008-2014
  publication-title: ONC Data Brief
– volume: 7
  start-page: 177
  year: 1986
  end-page: 188
  ident: bib38
  article-title: Meta-analysis in clinical trials
  publication-title: Control Clin Trials
– volume: 162
  start-page: 55
  year: 2015
  ident: bib23
  article-title: Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD Statement
  publication-title: Ann Intern Med
– volume: 9
  start-page: 784
  year: 2018
  ident: bib15
  article-title: Predicting outcome of endovascular treatment for acute ischemic stroke: potential value of machine learning algorithms
  publication-title: Front Neurol
– volume: 80
  start-page: 27
  year: 1993
  end-page: 38
  ident: bib30
  article-title: Bias reduction of maximum likelihood estimates
  publication-title: Biometrika
– volume: 19
  start-page: 322
  year: 2018
  ident: bib54
  article-title: Priority-Lasso: a simple hierarchical approach to the prediction of clinical outcome using multi-omics data
  publication-title: BMC Bioinformatics
– volume: 58
  start-page: 267
  year: 1996
  end-page: 288
  ident: bib29
  article-title: Regression shrinkage and selection via the lasso
  publication-title: J R Stat Soc Ser B
– volume: 20
  start-page: e262
  year: 2019
  end-page: e273
  ident: bib45
  article-title: Big data and machine learning algorithms for health-care delivery
  publication-title: Lancet Oncol
– year: 2018
  ident: bib32
  article-title: Flexible imputation of missing data
– volume: 16
  start-page: 987
  year: 2017
  ident: bib1
  article-title: Traumatic brain injury: integrated approaches to improve prevention, clinical care, and research
  publication-title: Lancet Neurol
– volume: 14
  start-page: e1002368
  year: 2017
  ident: bib44
  article-title: Evaluation of novel computerized tomography scoring systems in human traumatic brain injury: an observational, multicenter study
  publication-title: PLoS Med
– volume: 45
  start-page: 562
  year: 1958
  end-page: 565
  ident: bib35
  article-title: Two further applications of a model for binary regression
  publication-title: Biometrika
– volume: 110
  start-page: 12
  year: 2019
  end-page: 22
  ident: bib14
  article-title: A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models
  publication-title: J Clin Epidemiol
– volume: 15
  start-page: 83
  year: 2015
  ident: bib19
  article-title: Prediction of delayed graft function after kidney transplantation: comparison between logistic regression and machine learning methods
  publication-title: BMC Med Inform Decis Mak
– volume: 1
  start-page: 18
  year: 2018
  ident: bib50
  article-title: Scalable and accurate deep learning with electronic health records
  publication-title: NPJ Digit Med
– volume: 7
  start-page: 428
  year: 2018
  ident: bib17
  article-title: Prediction of acute kidney injury after liver transplantation: machine learning approaches vs. logistic regression model
  publication-title: J Clin Med
– volume: 44
  start-page: 837
  year: 1988
  end-page: 845
  ident: bib36
  article-title: Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach
  publication-title: Biometrics
– year: 2009
  ident: bib28
  article-title: Clinical prediction models: a practical approach to development, validation and updating
– volume: 44
  start-page: 368
  year: 2016
  end-page: 374
  ident: bib16
  article-title: Multicenter comparison of machine learning methods and conventional regression for predicting clinical deterioration on the wards
  publication-title: Crit Care Med
– volume: 76
  start-page: 67
  year: 2015
  end-page: 80
  ident: bib27
  article-title: Collaborative European neurotrauma effectiveness research in traumatic brain injury (CENTER-TBI): a prospective longitudinal observational study
  publication-title: Neurosurgery
– volume: 69
  start-page: 245
  year: 2016
  end-page: 247
  ident: bib34
  article-title: Prediction models need appropriate internal, internal-external, and external validation HHS Public Access
  publication-title: J Clin Epidemiol
– volume: 20
  start-page: 1
  year: 2019
  end-page: 32
  ident: bib41
  article-title: Tunability: importance of hyperparameters of machine learning algorithms
  publication-title: J Mach Learn Res
– volume: 35
  start-page: 1925
  year: 2014
  end-page: 1931
  ident: bib39
  article-title: Towards better clinical prediction models: Seven steps for development and an ABCD for validation
  publication-title: Eur Heart J
– volume: 46
  start-page: e481
  year: 2018
  end-page: e488
  ident: bib52
  article-title: Development and evaluation of an automated machine learning algorithm for in-hospital mortality risk adjustment among critical care patients
  publication-title: Crit Care Med
– volume: 17
  start-page: 1510
  year: 2014
  end-page: 1517
  ident: bib47
  article-title: Making big data open: data sharing in neuroimaging
  publication-title: Nat Neurosci
– volume: 13
  start-page: e0207192
  year: 2018
  ident: bib10
  article-title: Mortality prediction in patients with isolated moderate and severe traumatic brain injury using machine learning models
  publication-title: PLoS One
– year: 2004
  ident: bib31
  article-title: Multiple imputation for nonresponse in surveys
– volume: 37
  start-page: 202
  year: 2018
  end-page: 210
  ident: bib11
  article-title: Machine learning to predict in-hospital Morbidity and mortality after traumatic brain injury
  publication-title: J Neurotrauma
– volume: 74
  start-page: 167
  year: 2016
  end-page: 176
  ident: bib22
  article-title: A calibration hierarchy for risk models was defined: from utopia to empirical data
  publication-title: J Clin Epidemiol
– volume: 17
  start-page: 174
  year: 2017
  ident: bib42
  article-title: Comparison of machine learning techniques to predict all-cause mortality using fitness data: the Henry ford exercIse testing (FIT) project
  publication-title: BMC Med Inform Decis Mak
– volume: 24
  start-page: 239
  year: 2007
  end-page: 250
  ident: bib26
  article-title: IMPACT database of traumatic brain injury: design and description
  publication-title: J Neurotrauma
– volume: 30
  start-page: 232
  year: 2016
  end-page: 241
  ident: bib8
  article-title: Unsupervised random forest: a tutorial with case studies
  publication-title: J Chemom
– volume: 48
  start-page: 504
  year: 2017
  end-page: 510
  ident: bib5
  article-title: Machine learning for predicting outcomes in trauma
  publication-title: Shock
– volume: 7
  start-page: 21
  year: 2013
  ident: bib9
  article-title: Gradient boosting machines, a tutorial
  publication-title: Front Neurorobot
– volume: 29
  start-page: 31
  year: 1996
  end-page: 44
  ident: bib7
  article-title: Artificial neural networks: a tutorial
  publication-title: Computer (Long Beach Calif)
– volume: 23
  start-page: 907
  year: 2004
  end-page: 926
  ident: bib33
  article-title: Construction and validation of a prognostic model across several studies, with an application in superficial bladder cancer
  publication-title: Stat Med
– year: 2009
  ident: 10.1016/j.jclinepi.2020.03.005_bib28
– volume: 17
  start-page: 174
  year: 2017
  ident: 10.1016/j.jclinepi.2020.03.005_bib42
  article-title: Comparison of machine learning techniques to predict all-cause mortality using fitness data: the Henry ford exercIse testing (FIT) project
  publication-title: BMC Med Inform Decis Mak
  doi: 10.1186/s12911-017-0566-6
– volume: 9
  start-page: 543
  year: 2010
  ident: 10.1016/j.jclinepi.2020.03.005_bib4
  article-title: Early prognosis in traumatic brain injury: from prophecies to predictions
  publication-title: Lancet Neurol
  doi: 10.1016/S1474-4422(10)70065-X
– volume: 1
  start-page: 18
  year: 2018
  ident: 10.1016/j.jclinepi.2020.03.005_bib50
  article-title: Scalable and accurate deep learning with electronic health records
  publication-title: NPJ Digit Med
  doi: 10.1038/s41746-018-0029-1
– volume: 24
  start-page: 239
  year: 2007
  ident: 10.1016/j.jclinepi.2020.03.005_bib26
  article-title: IMPACT database of traumatic brain injury: design and description
  publication-title: J Neurotrauma
  doi: 10.1089/neu.2006.0036
– volume: 18
  start-page: 77
  year: 2018
  ident: 10.1016/j.jclinepi.2020.03.005_bib18
  article-title: A comparative study of logistic regression based machine learning techniques for prediction of early virological suppression in antiretroviral initiating HIV patients
  publication-title: BMC Med Inform Decis Mak
  doi: 10.1186/s12911-018-0659-x
– volume: 20
  start-page: 1
  year: 2019
  ident: 10.1016/j.jclinepi.2020.03.005_bib41
  article-title: Tunability: importance of hyperparameters of machine learning algorithms
  publication-title: J Mach Learn Res
– volume: 14
  start-page: e1002368
  year: 2017
  ident: 10.1016/j.jclinepi.2020.03.005_bib44
  article-title: Evaluation of novel computerized tomography scoring systems in human traumatic brain injury: an observational, multicenter study
  publication-title: PLoS Med
  doi: 10.1371/journal.pmed.1002368
– volume: 20
  start-page: e262
  year: 2019
  ident: 10.1016/j.jclinepi.2020.03.005_bib45
  article-title: Big data and machine learning algorithms for health-care delivery
  publication-title: Lancet Oncol
  doi: 10.1016/S1470-2045(19)30149-4
– volume: 7
  start-page: 177
  year: 1986
  ident: 10.1016/j.jclinepi.2020.03.005_bib38
  article-title: Meta-analysis in clinical trials
  publication-title: Control Clin Trials
  doi: 10.1016/0197-2456(86)90046-2
– volume: 9
  start-page: 784
  year: 2018
  ident: 10.1016/j.jclinepi.2020.03.005_bib15
  article-title: Predicting outcome of endovascular treatment for acute ischemic stroke: potential value of machine learning algorithms
  publication-title: Front Neurol
  doi: 10.3389/fneur.2018.00784
– volume: 29
  start-page: 31
  year: 1996
  ident: 10.1016/j.jclinepi.2020.03.005_bib7
  article-title: Artificial neural networks: a tutorial
  publication-title: Computer (Long Beach Calif)
– year: 2009
  ident: 10.1016/j.jclinepi.2020.03.005_bib21
– volume: 80
  start-page: 27
  year: 1993
  ident: 10.1016/j.jclinepi.2020.03.005_bib30
  article-title: Bias reduction of maximum likelihood estimates
  publication-title: Biometrika
  doi: 10.1093/biomet/80.1.27
– volume: 25
  start-page: 719
  year: 2008
  ident: 10.1016/j.jclinepi.2020.03.005_bib3
  article-title: Classification of traumatic brain injury for targeted therapies
  publication-title: J Neurotrauma
  doi: 10.1089/neu.2008.0586
– volume: 13
  start-page: e0207192
  year: 2018
  ident: 10.1016/j.jclinepi.2020.03.005_bib10
  article-title: Mortality prediction in patients with isolated moderate and severe traumatic brain injury using machine learning models
  publication-title: PLoS One
  doi: 10.1371/journal.pone.0207192
– volume: 35
  start-page: 1
  year: 2016
  ident: 10.1016/j.jclinepi.2020.03.005_bib49
  article-title: Adoption of electronic health record systems among U.S. non-federal acute care hospitals: 2008-2014
  publication-title: ONC Data Brief
– volume: 2
  start-page: 121
  year: 1998
  ident: 10.1016/j.jclinepi.2020.03.005_bib6
  article-title: A tutorial on support vector machines for pattern recognition
  publication-title: Data Mining Knowledge Discovery
  doi: 10.1023/A:1009715923555
– volume: 1
  start-page: e76
  year: 2016
  ident: 10.1016/j.jclinepi.2020.03.005_bib2
  article-title: Epidemiology of traumatic brain injuries in Europe: a cross-sectional analysis
  publication-title: Lancet Public Heal
  doi: 10.1016/S2468-2667(16)30017-2
– volume: 19
  start-page: 322
  year: 2018
  ident: 10.1016/j.jclinepi.2020.03.005_bib54
  article-title: Priority-Lasso: a simple hierarchical approach to the prediction of clinical outcome using multi-omics data
  publication-title: BMC Bioinformatics
  doi: 10.1186/s12859-018-2344-6
– volume: 30
  start-page: 232
  year: 2016
  ident: 10.1016/j.jclinepi.2020.03.005_bib8
  article-title: Unsupervised random forest: a tutorial with case studies
  publication-title: J Chemom
  doi: 10.1002/cem.2790
– volume: 7
  start-page: 21
  year: 2013
  ident: 10.1016/j.jclinepi.2020.03.005_bib9
  article-title: Gradient boosting machines, a tutorial
  publication-title: Front Neurorobot
  doi: 10.3389/fnbot.2013.00021
– volume: 44
  start-page: 368
  year: 2016
  ident: 10.1016/j.jclinepi.2020.03.005_bib16
  article-title: Multicenter comparison of machine learning methods and conventional regression for predicting clinical deterioration on the wards
  publication-title: Crit Care Med
  doi: 10.1097/CCM.0000000000001571
– volume: 46
  start-page: e481
  year: 2018
  ident: 10.1016/j.jclinepi.2020.03.005_bib52
  article-title: Development and evaluation of an automated machine learning algorithm for in-hospital mortality risk adjustment among critical care patients
  publication-title: Crit Care Med
  doi: 10.1097/CCM.0000000000003011
– volume: 58
  start-page: 267
  year: 1996
  ident: 10.1016/j.jclinepi.2020.03.005_bib29
  article-title: Regression shrinkage and selection via the lasso
  publication-title: J R Stat Soc Ser B
  doi: 10.1111/j.2517-6161.1996.tb02080.x
– volume: 17
  start-page: 1510
  year: 2014
  ident: 10.1016/j.jclinepi.2020.03.005_bib47
  article-title: Making big data open: data sharing in neuroimaging
  publication-title: Nat Neurosci
  doi: 10.1038/nn.3818
– year: 2001
  ident: 10.1016/j.jclinepi.2020.03.005_bib20
– year: 2018
  ident: 10.1016/j.jclinepi.2020.03.005_bib32
– volume: 5
  start-page: e165
  year: 2008
  ident: 10.1016/j.jclinepi.2020.03.005_bib25
  article-title: Predicting outcome after traumatic brain injury: development and international validation of prognostic scores based on admission characteristics
  publication-title: PLoS Med
  doi: 10.1371/journal.pmed.0050165
– volume: 23
  start-page: 907
  year: 2004
  ident: 10.1016/j.jclinepi.2020.03.005_bib33
  article-title: Construction and validation of a prognostic model across several studies, with an application in superficial bladder cancer
  publication-title: Stat Med
  doi: 10.1002/sim.1691
– volume: 7
  start-page: e017199
  year: 2017
  ident: 10.1016/j.jclinepi.2020.03.005_bib53
  article-title: Prediction of early unplanned intensive care unit readmission in a UK tertiary care hospital: a cross-sectional machine learning approach
  publication-title: BMJ Open
  doi: 10.1136/bmjopen-2017-017199
– volume: 69
  start-page: 245
  year: 2016
  ident: 10.1016/j.jclinepi.2020.03.005_bib34
  article-title: Prediction models need appropriate internal, internal-external, and external validation HHS Public Access
  publication-title: J Clin Epidemiol
  doi: 10.1016/j.jclinepi.2015.04.005
– volume: 162
  start-page: 55
  year: 2015
  ident: 10.1016/j.jclinepi.2020.03.005_bib23
  article-title: Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD Statement
  publication-title: Ann Intern Med
  doi: 10.7326/M14-0697
– volume: 35
  start-page: 1925
  year: 2014
  ident: 10.1016/j.jclinepi.2020.03.005_bib39
  article-title: Towards better clinical prediction models: Seven steps for development and an ABCD for validation
  publication-title: Eur Heart J
  doi: 10.1093/eurheartj/ehu207
– volume: 78
  start-page: 83
  year: 2016
  ident: 10.1016/j.jclinepi.2020.03.005_bib46
  article-title: Modern modeling techniques had limited external validity in predicting mortality from traumatic brain injury
  publication-title: J Clin Epidemiol
  doi: 10.1016/j.jclinepi.2016.03.002
– volume: 15
  start-page: 83
  year: 2015
  ident: 10.1016/j.jclinepi.2020.03.005_bib19
  article-title: Prediction of delayed graft function after kidney transplantation: comparison between logistic regression and machine learning methods
  publication-title: BMC Med Inform Decis Mak
  doi: 10.1186/s12911-015-0206-y
– volume: 74
  start-page: 167
  year: 2016
  ident: 10.1016/j.jclinepi.2020.03.005_bib22
  article-title: A calibration hierarchy for risk models was defined: from utopia to empirical data
  publication-title: J Clin Epidemiol
  doi: 10.1016/j.jclinepi.2015.12.005
– volume: 25
  start-page: 969
  year: 2018
  ident: 10.1016/j.jclinepi.2020.03.005_bib55
  article-title: Design and implementation of a standardized framework to generate and evaluate patient-level prediction models using observational healthcare data
  publication-title: J Am Med Inform Assoc
  doi: 10.1093/jamia/ocy032
– volume: 21
  start-page: 128
  year: 2010
  ident: 10.1016/j.jclinepi.2020.03.005_bib37
  article-title: Assessing the performance of prediction models: a framework for traditional and novel measures
  publication-title: Epidemiology
  doi: 10.1097/EDE.0b013e3181c30fb2
– volume: 54
  start-page: 110
  year: 2019
  ident: 10.1016/j.jclinepi.2020.03.005_bib12
  article-title: Comparison between logistic regression and machine learning algorithms on survival prediction of traumatic brain injuries
  publication-title: J Crit Care
  doi: 10.1016/j.jcrc.2019.08.010
– volume: 44
  start-page: 837
  year: 1988
  ident: 10.1016/j.jclinepi.2020.03.005_bib36
  article-title: Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach
  publication-title: Biometrics
  doi: 10.2307/2531595
– volume: 319
  start-page: 1317
  year: 2018
  ident: 10.1016/j.jclinepi.2020.03.005_bib51
  article-title: Big data and machine learning in health care
  publication-title: JAMA
  doi: 10.1001/jama.2017.18391
– volume: 14
  start-page: 137
  year: 2014
  ident: 10.1016/j.jclinepi.2020.03.005_bib13
  article-title: Modern modelling techniques are data hungry: a simulation study for predicting dichotomous endpoints
  publication-title: BMC Med Res Methodol
  doi: 10.1186/1471-2288-14-137
– volume: 45
  start-page: 562
  year: 1958
  ident: 10.1016/j.jclinepi.2020.03.005_bib35
  article-title: Two further applications of a model for binary regression
  publication-title: Biometrika
  doi: 10.1093/biomet/45.3-4.562
– volume: 45
  start-page: 5
  year: 2001
  ident: 10.1016/j.jclinepi.2020.03.005_bib40
  article-title: Random Forests
  publication-title: Mach Learn
  doi: 10.1023/A:1010933404324
– year: 2004
  ident: 10.1016/j.jclinepi.2020.03.005_bib31
– volume: 98
  start-page: 691
  year: 2012
  ident: 10.1016/j.jclinepi.2020.03.005_bib24
  article-title: Risk prediction models: II. External validation, model updating, and impact assessment
  publication-title: Heart
  doi: 10.1136/heartjnl-2011-301247
– volume: 16
  start-page: 987
  year: 2017
  ident: 10.1016/j.jclinepi.2020.03.005_bib1
  article-title: Traumatic brain injury: integrated approaches to improve prevention, clinical care, and research
  publication-title: Lancet Neurol
  doi: 10.1016/S1474-4422(17)30371-X
– volume: 7
  start-page: 428
  year: 2018
  ident: 10.1016/j.jclinepi.2020.03.005_bib17
  article-title: Prediction of acute kidney injury after liver transplantation: machine learning approaches vs. logistic regression model
  publication-title: J Clin Med
  doi: 10.3390/jcm7110428
– volume: 26
  start-page: 5499
  year: 2007
  ident: 10.1016/j.jclinepi.2020.03.005_bib43
  article-title: Practical experiences on the necessity of external validation
  publication-title: Stat Med
  doi: 10.1002/sim.3069
– volume: 48
  start-page: 504
  year: 2017
  ident: 10.1016/j.jclinepi.2020.03.005_bib5
  article-title: Machine learning for predicting outcomes in trauma
  publication-title: Shock
  doi: 10.1097/SHK.0000000000000898
– volume: 110
  start-page: 12
  year: 2019
  ident: 10.1016/j.jclinepi.2020.03.005_bib14
  article-title: A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models
  publication-title: J Clin Epidemiol
  doi: 10.1016/j.jclinepi.2019.02.004
– volume: 37
  start-page: 202
  year: 2018
  ident: 10.1016/j.jclinepi.2020.03.005_bib11
  article-title: Machine learning to predict in-hospital Morbidity and mortality after traumatic brain injury
  publication-title: J Neurotrauma
  doi: 10.1089/neu.2018.6276
– volume: 11
  start-page: 651
  year: 2012
  ident: 10.1016/j.jclinepi.2020.03.005_bib48
  article-title: The changing landscape of traumatic brain injury research
  publication-title: Lancet Neurol
  doi: 10.1016/S1474-4422(12)70166-7
– volume: 76
  start-page: 67
  year: 2015
  ident: 10.1016/j.jclinepi.2020.03.005_bib27
  article-title: Collaborative European neurotrauma effectiveness research in traumatic brain injury (CENTER-TBI): a prospective longitudinal observational study
  publication-title: Neurosurgery
  doi: 10.1227/NEU.0000000000000575
SSID ssj0017075
Score 2.6399415
Snippet We aimed to explore the added value of common machine learning (ML) algorithms for prediction of outcome for moderate and severe traumatic brain injury. We...
AbstractObjectiveWe aimed to explore the added value of common machine learning (ML) algorithms for prediction of outcome for moderate and severe traumatic...
ObjectiveWe aimed to explore the added value of common machine learning (ML) algorithms for prediction of outcome for moderate and severe traumatic brain...
We aimed to explore the added value of common machine learning (ML) algorithms for prediction of outcome for moderate and severe traumatic brain...
Objective - We aimed to explore the added value of common machine learning (ML) algorithms for prediction of outcome for moderate and severe traumatic brain...
Objective: We aimed to explore the added value of common machine learning (ML) algorithms for prediction of outcome for moderate and severe traumatic brain...
OBJECTIVE: We aimed to explore the added value of common machine learning (ML) algorithms for prediction of outcome for moderate and severe traumatic brain...
SourceID unpaywall
swepub
liege
hal
cristin
proquest
pubmed
crossref
elsevier
SourceType Open Access Repository
Aggregation Database
Index Database
Enrichment Source
Publisher
StartPage 95
SubjectTerms Adult
Algorithms
Artificial neural networks
Brain
Brain Injuries, Traumatic - therapy
Calibration
Cohort analysis
Cohort study
Coma
Confidence intervals
Data science
Datasets
Decision Making, Computer-Assisted
Epidemiology
Female
Glasgow Coma Scale
Head injuries
Human health and pathology
Humans
Internal Medicine
Laboratories
Learning algorithms
Life Sciences
Logistic Models
Machine Learning
Male
Medical disciplines: 700
Medical prognosis
Medical technology: 620
Medisinsk teknologi: 620
Medisinske Fag: 700
Middle Aged
Models, Statistical
Mortality
Neural networks
Neurosciences & behavior
Neurosciences & comportement
Prediction
Prediction models
Prognosis
Regression analysis
Regression models
Sciences sociales & comportementales, psychologie
Social & behavioral sciences, psychology
Support vector machines
Technology: 500
Teknologi: 500
Traumatic brain injury
Variables
VDP
SummonAdditionalLinks – databaseName: ProQuest Central
  dbid: BENPR
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3rb9MwELe2VuLxAfFeYCCDgE9kS-LETj4gVGDThGiFgKF9O9mJ07V0aWmbIf577vJiSGNMSK0UpWfl6rvz_Rzfg7FnuRbKBkq76F0SN5QydTUCZ1eYPMpjnShTZXgPR_LgMHx_FB1tsFGbC0Nhle2aWC3U2Tyld-S7BI1lGONu5PXiu0tdo-h0tW2hoZvWCtmrqsTYJusHVBmrx_pv9kYfP3XnCqouvevFSeQiUJBncoanO1NKRrSLCe4aA68ufUpJTmllbcXfHNfmMUVQ9md0xn0eTO1qkF5nV8tioX_-0LPZGR-2f5PdaMAnH9Tacott2OI2uzJsjtfvsPWwCq20vOklMeZ6NsZJWB-frPiiTjGwGS_m3FRZQJzeu_OlHdfBtAWv-uqsONJxCvwq5lQFupI9nxR8vdRlVSGWG2pMgbemKNG77HB_78vbA7dpy-CmSiZrN4wyLzeJMV5ofJkiYIsjmeFHZZEOMi8zVmZxEnoZissTIkop-TXUcSbjMMmluMd6xbywW4wLBFOJ8dHy8zBUqTDa5kKJVEs_9aXVDttqZh8KtAgqsCwUUFtR32FRKw5Im3Lm1FVjBm3c2hRagQIJFDwBKFCH7XbjFnVBj3-OUK20oU1XxQUW0Of830i7ataJFfiwCsCDz6SQpI8Ip6nFgHBY0o1soFANcS711Keokt2fo_rhB4MPQPeofwBuKP1TnL6XlcbCfGkmcBpUZNV1ORuDTsFYQGQeA27PRYD8bLeKDR3zv03SYU-6n3F5ojMnXdh5iTSECHETHiFb92uD6DhDX4LwKJIOe15byB88v5t8HSBHY_yWEKNLjh324iK68qQEX_lC-ecTNre-4ZWFUKGvQr69ziQvqQ0PLp6Jh-waEdfBhNust16W9hHC1rV53KxFvwABe5bQ
  priority: 102
  providerName: ProQuest
– databaseName: Unpaywall
  dbid: UNPAY
  link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3rb9MwELe2VuLxgTcsMJBBwCey5mUn-VgBU4XohASbxqeTnThduy6t2mQI_nru8mJoAzakVkrdc3uN73y_q-_B2MtM-aHxQmWjdYntQMrEVgicbV9nIotUHOoqw3u8J0f7wYdDcbjB2k6FFFU5o5xAs5xW-3Rz_wafnSgWaNoR71MNO-EPlmm2yfpSIATvsf7-3qfh1woxxsImOnK0IvSQROy5ZzKDZ78-Ht1-py5wSqlMSaVT-Z_M0-YRxUn253SSfREY7SqN3mTXy3ypvn9T8_kZS7V7mx20-T51gMrxTlnoneTH-fKPV7sJd9itBrvyYU13l22Y_B67Nm5O5--zYlxFZhretKKYcDWfLFbT4uhkzZd1hoJJeb7gukoi4vS3PV-ZSR2Lm_OqLc-aIx2nuLF8QUWkK9Hh05wXK1VWBWa5pr4WODRDgXjA9nfff3k7spuuDnYSyriwA5E6mY61dgLtygTxXiRkio8wFcpLnVQbmUZx4KRBRJ3mREK5s4GKUhkFcSb9h6yXL3KzxbiPWCzWLm4cWRCEia-VyfzQT5R0E1caZbGtZlkhR4Wi-sx-CNSV1LWYaNcZkqYaOjXlmEMb9jaDdg2AJAUcH1BSLDbo5i3reiD_nBG2YgRttivuz4Am6_9mmnWzzazBhbUHDpyTC4vF3cwGSdUI6VLf-gJlvftxVH58NPwINEbtB9AfdU_x9r2pVAEWKz2FU68iq67L-QRUAtoAAvsI0Lv3PeRnu9UY6JgnZ1fiGseBxZ53b-PuRkdWKjeLEmkIUKIPL5CtR7WmdZyhKUJ0JaTFXtWq9xvP76YHQ-Rogs8SIrTokcVe_42uPCnBDV0_dC8mbIaO8cpAEKKpQ76dTtcvKQ2Prz7lCbtBr-r4xG3WK1aleYpIuNDPmn3vJ_tfsBY
  priority: 102
  providerName: Unpaywall
Title Machine learning algorithms performed no better than regression models for prognostication in traumatic brain injury
URI https://www.clinicalkey.com/#!/content/1-s2.0-S0895435619308753
https://www.clinicalkey.es/playcontent/1-s2.0-S0895435619308753
https://dx.doi.org/10.1016/j.jclinepi.2020.03.005
https://www.ncbi.nlm.nih.gov/pubmed/32201256
https://www.proquest.com/docview/2425648094
https://www.proquest.com/docview/2381849555
http://hdl.handle.net/10037/20851
https://hal.science/hal-04831821
http://orbi.ulg.ac.be/handle/2268/249323
https://urn.kb.se/resolve?urn=urn:nbn:se:oru:diva-81118
https://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-171371
http://kipublications.ki.se/Default.aspx?queryparsed=id:143918942
http://www.jclinepi.com/article/S0895435619308753/pdf
UnpaywallVersion publishedVersion
Volume 122
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Baden-Württemberg Complete Freedom Collection (Elsevier)
  customDbUrl:
  eissn: 1878-5921
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0017075
  issn: 0895-4356
  databaseCode: GBLVA
  dateStart: 20110101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
– providerCode: PRVESC
  databaseName: Elsevier ScienceDirect
  customDbUrl:
  eissn: 1878-5921
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0017075
  issn: 0895-4356
  databaseCode: .~1
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
– providerCode: PRVESC
  databaseName: Elsevier ScienceDirect Freedom Collection
  customDbUrl:
  eissn: 1878-5921
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0017075
  issn: 0895-4356
  databaseCode: AIKHN
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
– providerCode: PRVESC
  databaseName: Elsevier SD Complete Freedom Collection
  customDbUrl:
  eissn: 1878-5921
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0017075
  issn: 0895-4356
  databaseCode: ACRLP
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
– providerCode: PRVLSH
  databaseName: Elsevier Journals
  customDbUrl:
  mediaType: online
  eissn: 1878-5921
  dateEnd: 99991231
  omitProxy: true
  ssIdentifier: ssj0017075
  issn: 0895-4356
  databaseCode: AKRWK
  dateStart: 19880101
  isFulltext: true
  providerName: Library Specific Holdings
– providerCode: PRVPQU
  databaseName: Health & Medical Collection (Proquest)
  customDbUrl:
  eissn: 1878-5921
  dateEnd: 20250901
  omitProxy: true
  ssIdentifier: ssj0017075
  issn: 0895-4356
  databaseCode: 7X7
  dateStart: 20030101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/healthcomplete
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: ProQuest Central
  customDbUrl: http://www.proquest.com/pqcentral?accountid=15518
  eissn: 1878-5921
  dateEnd: 20250901
  omitProxy: true
  ssIdentifier: ssj0017075
  issn: 0895-4356
  databaseCode: BENPR
  dateStart: 20030101
  isFulltext: true
  titleUrlDefault: https://www.proquest.com/central
  providerName: ProQuest
– providerCode: PRVPQU
  databaseName: Proquest Public Health Database
  customDbUrl:
  eissn: 1878-5921
  dateEnd: 20250901
  omitProxy: true
  ssIdentifier: ssj0017075
  issn: 0895-4356
  databaseCode: 8C1
  dateStart: 20030101
  isFulltext: true
  titleUrlDefault: https://search.proquest.com/publichealth
  providerName: ProQuest
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpR1rb9Mw0BqbxOMD4r3AQAYBn8iaNImdfCxlU3m0moCh7tPJTpwupUurthniC7-du7y0iQETSG3iumf14vM9XN-Dseep8qTpSmWjdolsX4jYVmg4255OgzRUkdRlhPdwJAaH_rtxMN5g_SYWhtwqa9lfyfRSWtc9nXo2O4ss63xywihAZY87AMpqF1DGT9-XVMVg90fr5uHKKtkuAdsEfSZKeLo7pfBDs8hwn9h1qmSnFNYUl_yV_05VXTkmn8mtGZ1qX2SYtllHb7BrRb5Q37-p2eyM1tq_xW7W5ibvVU90m22Y_A67OqwP1O-y9bB0pjS8rh4x4Wo2mS-z9fHJii-qoAKT8HzOdRn3w-mfdr40k8p9NudlJZ0VRzhOrl75nPI-l9TmWc7XS1WUOWG5plIU2DVFGt5jh_t7n_sDuy7EYMdSRGvbDxIn1ZHWjq9dEaOJFgYiwZdMAtVNnEQbkYSR7yR-SMXhgpjCXX0VJiL0o1R499lmPs_NNuMemk-RdpHXUyRW7GllUk96sRJu7AqjLLZdzz7kyAOUUtmTQIVEXYsFDTkgrhOYUx2NGTSealNoCApEUHA8QIJarNOOW1QpPP46QjbUhiZAFUUqoJb5t5FmVUuGFbiw6oIDv6xei0XtyHMMcKlffYZLsn04yhg-6H0A6qOKAbiFdE9x-l6VKxbmS53BabcEK9vFbAIqBm0AbfEQcEPudRGfnWZhQ4s87U8F0jjyLfa0_RoFEp0yqdzMC4QhGxC33QGi9aBiiBYz1B5oEAXCYi8qDjmH85vsSw8xmuC7gBCVcGixl3-CK04KcKXrSfdiwLrrK7YMoGgIJOLttCx5ydXw8D8o84hdp0-Vb-EO21wvC_MYrdi1flKKKbzKscRr2Mf2Vu_t-8EI76_3Rgcf8X44Ougd_QSfnKFb
linkProvider Elsevier
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3db9MwELf2ITF4QHwvMMAgxhNhSZzYyQNC1cbUsXUvbGhvxk6crqVLS5Ns2j_F38hdvhjSGBPSpFaKXDu5-s53P8f3QcibVDFhPKFssC6R7XMe2wqAs810GqShioSuIrwH-7x_6H8-Co4WyM82FgbdKludWCnqZBrjO_INhMbcD2E38nH2w8aqUXi62pbQqMVi15yfwZYt_7CzBfxd97ztTwebfbupKmDHgkeF7QeJk-pIa8fXLo8Bb4QBT-AjkkB5iZNow5Mw8p0EnuYwFsQYu-mrMOGhH6WcwX0XybLPPIGKINzsXEpcUSf2dcIosAGG8AsRyeP3Ywx1NLMR7Ek9p06siiFUcbWWs7-ZxcVj9M9cnuAJ-mUguMtweoeslNlMnZ-pyeSChdy-R-420Jb2alm8TxZM9oDcGjSH9w9JMagcNw1tKlUMqZoMYYqL45OczuoABpPQbEp1FWNE8a0-nZth7aqb0apqT06hH0W3smyKOaYryaKjjBZzVVb5Z6nGshfQNAZ5eUQOb4Q9j8lSNs3MKqEMoFqkXdArqe-LmGllUiZYrLgbu9woi6w2sy8zWG-YvpkJiUVLXYsELTtk3CRLx5odE9l6xY1ly1CJDJUOk8BQi2x042Z1upB_jhAtt2UbDAvqW4JF-7-RJm-0UC5dmXvSkV9QIFEeAaxjAQNmkagb2QCtGkBd66mvQSS7P4fZyfu9PYltWJ0AtqvuKUzfu0pi5XSuR_LUq7pV1-VkKFUstZGA-0MJm3_mAT1rrWDLjvjfC94ir7qfQfnhiZbKzLSEPog3YYsfAFlP6gXRUQaWCsBXwC2yXq-QP2jeGn3tAUVD-JYyBIMfWuTtVf3Kk1K6wmXCvbxj0_Qdroz0BVhCoNvpluQ1peHp1TPxkqz0DwZ7cm9nf_cZuY0Da7fFNbJUzEvzHAByoV9UWomSbzetBn8BZBbLuQ
linkToPdf http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3rb9MwELf2kAZ8QLwXGGAQ4xNhSZzYyQeEJsY02ENIMLRvh504XUuXlrbZtH-Nv467vBjSGBPSpFaqUru5-s53v4vvwdiLXAtlA6VdtC6JG0qZuhqBsytMHuWxTpSpMrx39-TWfvjxIDqYYz_bXBgKq2x1YqWos1FKz8jXCBrLMEZvZC1vwiI-bWy-Hf9wqYMUnbS27TRqEdm2pyfovk3ffNhAXq8Gweb7L--23KbDgJsqmczcMMq83CTGeKHxZYrYI45khi-VRTrIvMxYmcVJ6GV4Z0-IKKU8zlDHmYzDJJcCf3eeLSohEgonVAeds-erusivFyeRi5BEnslOHrweUNqjHffRPw28usgqpVOl1b4u_mYi5w8pVnNxSKfp5wHirtrpDXatLMb69EQPh2es5eYtdrOBuXy9lsvbbM4Wd9jSbnOQf5fNdqsgTsubrhU9roc9XOLZ4dGUj-tkBpvxYsRNlW_E6Qk_n9heHbZb8KqDz5TjOE4hZsWI6k1XUsb7BZ9NdFnVouWGWmDgpQHKzj22fyXsuc8WilFhlxkXCNsS46OOycNQpcJomwslUi391JdWO2y5WX0ocO9RKWehgBqY-g6LWnZA2hROp_4dQ2gj5AbQMhSIoeAJQIY6bK2bN65Lh_xzhmq5DW1iLKpyQOv2fzPttNFIU_BhGoAHn0kgSR4RuFMzA-GwpJvZgK4aTF3qrs9RJLs_R5XKt9Z3gK5RpwJ0Xf1jXL5XlcTCaGL6cBxUw6rP5bAHOgVjAX2AGIIQfQmkZ6UVbOiI_735Hfas-xoVIZ1u6cKOShxD2BPd_QjJelBviI4ytFoIxCLpsNV6h_xB80b_6zpS1MN3CTEa_9hhLy8aVx6V4CtfKP_8gc2l7_jJQqjQKiLdXrclLykNDy9eiadsCRUg7HzY237ErtO8OoJxhS3MJqV9jFh5Zp5USomzb1etBX8B5KXQKA
linkToUnpaywall http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3rb9MwELe2VuLxgTcsMJBBwCey5mUn-VgBU4XohASbxqeTnThduy6t2mQI_nru8mJoAzakVkrdc3uN73y_q-_B2MtM-aHxQmWjdYntQMrEVgicbV9nIotUHOoqw3u8J0f7wYdDcbjB2k6FFFU5o5xAs5xW-3Rz_wafnSgWaNoR71MNO-EPlmm2yfpSIATvsf7-3qfh1woxxsImOnK0IvSQROy5ZzKDZ78-Ht1-py5wSqlMSaVT-Z_M0-YRxUn253SSfREY7SqN3mTXy3ypvn9T8_kZS7V7mx20-T51gMrxTlnoneTH-fKPV7sJd9itBrvyYU13l22Y_B67Nm5O5--zYlxFZhretKKYcDWfLFbT4uhkzZd1hoJJeb7gukoi4vS3PV-ZSR2Lm_OqLc-aIx2nuLF8QUWkK9Hh05wXK1VWBWa5pr4WODRDgXjA9nfff3k7spuuDnYSyriwA5E6mY61dgLtygTxXiRkio8wFcpLnVQbmUZx4KRBRJ3mREK5s4GKUhkFcSb9h6yXL3KzxbiPWCzWLm4cWRCEia-VyfzQT5R0E1caZbGtZlkhR4Wi-sx-CNSV1LWYaNcZkqYaOjXlmEMb9jaDdg2AJAUcH1BSLDbo5i3reiD_nBG2YgRttivuz4Am6_9mmnWzzazBhbUHDpyTC4vF3cwGSdUI6VLf-gJlvftxVH58NPwINEbtB9AfdU_x9r2pVAEWKz2FU68iq67L-QRUAtoAAvsI0Lv3PeRnu9UY6JgnZ1fiGseBxZ53b-PuRkdWKjeLEmkIUKIPL5CtR7WmdZyhKUJ0JaTFXtWq9xvP76YHQ-Rogs8SIrTokcVe_42uPCnBDV0_dC8mbIaO8cpAEKKpQ76dTtcvKQ2Prz7lCbtBr-r4xG3WK1aleYpIuNDPmn3vJ_tfsBY
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Machine+learning+algorithms+performed+no+better+than+regression+models+for+prognostication+in+traumatic+brain+injury&rft.jtitle=Journal+of+clinical+epidemiology&rft.au=Gravesteijn%2C+Benjamin+Y&rft.au=Nieboer%2C+Daan&rft.au=Ercole%2C+Ari&rft.au=Lingsma%2C+Hester+F&rft.date=2020-06-01&rft.issn=0895-4356&rft.volume=122&rft.spage=95&rft_id=info:doi/10.1016%2Fj.jclinepi.2020.03.005&rft.externalDocID=oai_DiVA_org_umu_171371
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0895-4356&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0895-4356&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0895-4356&client=summon