CoChat
Sign Up
Cited by 93Traumatic Brain Injury and Neurovascular DisturbancesTraumatic Brain Injury ResearchTrauma and Emergency Care Studies

Clustering identifies endotypes of traumatic brain injury in an intensive care cohort: a CENTER-TBI study

Open access
Åkerlund, Cecilia A. I., Holst, Anders, Stocchetti, Nino, Steyerberg, Ewout W., Menon, David K., Ercole, Ari, Nelson, David W., the CENTER-TBI Participants and Investigators +251 more·2022·Critical Care
DOI 10.1186/s13054-022-04079-wPMC PMC9327174
Open this paper in CoChat — free accountOpen PDF

Abstract

Background: While the Glasgow coma scale (GCS) is one of the strongest outcome predictors, the current classification of traumatic brain injury (TBI) as ‘mild’, ‘moderate’ or ‘severe’ based on this fails to capture enormous heterogeneity in pathophysiology and treatment response. We hypothesized that data-driven characterization of TBI could identify distinct endotypes and give mechanistic insights. Methods: We developed an unsupervised statistical clustering model based on a mixture of probabilistic graphs for presentation (< 24 h) demographic, clinical, physiological, laboratory and imaging data to identify subgroups of TBI patients admitted to the intensive care unit in the CENTER-TBI dataset ( N = 1,728). A cluster similarity index was used for robust determination of optimal cluster number. Mutual information was used to quantify feature importance and for cluster interpretation. Results: Six stable endotypes were identified with distinct GCS and composite systemic metabolic stress profiles, distinguished by GCS, blood lactate, oxygen saturation, serum creatinine, glucose, base excess, pH, arterial partial pressure of carbon dioxide, and body temperature. Notably, a cluster with ‘moderate’ TBI (by traditional classification) and deranged metabolic profile, had a worse outcome than a cluster with ‘severe’ GCS and a normal metabolic profile. Addition of cluster labels significantly improved the prognostic precision of the IMPACT (International Mission for Prognosis and Analysis of Clinical trials in TBI) extended model, for prediction of both unfavourable outcome and mortality (both p < 0.001). Conclusions: Six stable and clinically distinct TBI endotypes were identified by probabilistic unsupervised clustering. In addition to presenting neurology, a profile of biochemical derangement was found to be an important distinguishing feature that was both biologically plausible and associated with outcome. Our work motivates refining current TBI classifications with factors describing metabolic stress. Such data-driven clusters suggest TBI endotypes that merit investigation to identify bespoke treatment strategies to improve care. Trial registration The core study was registered with ClinicalTrials.gov, number NCT02210221 , registered on August 06, 2014, with Resource Identification Portal (RRID: SCR_015582).

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1186/s13054-022-04079-w

Cites

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Conducting an RCT on the six AI-identified TBI endotypes would be unfeasible without AI stratification.

    “In the TBI example cited, conducting an RCT on the six AI-identified endotypes—such as patients with moderate GCS but severe metabolic derangement—would be unfeasible without AI stratification [38].”

    From Implementing Artificial Intelligence in Critical Care Medicine: a consensus of 22. (2025) · cites this paper as [38]

    The Results identify six endotypes, including a group with moderate GCS and a deranged metabolic profile. The Discussion proposes investigating whether the clusters responded differently to treatments in earlier RCTs; it does not say that conducting an RCT would be unfeasible without AI stratification. Page numbers are unavailable in our copy. (LLM, conf=0.88)

    Experimental — accuracy not yet measured

  • In a large ICU cohort of patients with traumatic brain injury, unsupervised clustering identified six distinct subgroups based on combined neurological and metabolic profiles.

    “In a large ICU cohort of patients with traumatic brain injury (TBI), unsupervised clustering identified six distinct subgroups, based on combined neurological and metabolic profiles. [38]”

    From Implementing Artificial Intelligence in Critical Care Medicine: a consensus of 22. (2025) · cites this paper as [38]

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

The citation lists haven’t been fetched yet

References 30 · Cited by 93

Research works printed but not linked: 27

  1. [1]Rubiano AM Carney N Chesnut R Puyana JC Global neurotrauma research challenges and opportunities Nature 2015 527 7578 S193 S197 10.1038/nature16035 26580327 · DOI
  2. [2]Roozenbeek B Maas AIR Menon DK Changing patterns in the epidemiology of traumatic brain injury Nat Rev Neurol 2013 9 4 231 236 10.1038/nrneurol.2013.22 23443846 · DOI
  3. [3]Bragge P Synnot A Maas AI Menon DK Cooper DJ Rosenfeld JV A state-of-the-science overview of randomized controlled trials evaluating acute management of moderate-to-severe traumatic brain injury J Neurotrauma 2016 33 16 1461 1478 10.1089/neu.2015.4233 26711675 PMC5003006 · DOI
  4. [4]Steyerberg EW Wiegers E Sewalt C Buki A Citerio G De Keyser V Case-mix, care pathways, and outcomes in patients with traumatic brain injury in CENTER-TBI: a European prospective, multicentre, longitudinal, cohort study Lancet Neurol 2019 18 10 923 934 10.1016/S1474-4422(19)30232-7 31526754 · DOI
  5. [5]Chesnut RM Temkin N Carney N Dikmen S Rondina C Videtta W A trial of intracranial-pressure monitoring in traumatic brain injury N Engl J Med 2012 36726367 27 2471 2481 10.1056/NEJMoa1207363 PMC3565432 23234472 · DOI
  6. [6]Huijben JA Wiegers EJA Lingsma HF Citerio G Maas AIR Menon DK Changing care pathways and between-center practice variations in intensive care for traumatic brain injury across Europe: a CENTER-TBI analysis Intensive Care Med 2020 46 5 995 1004 10.1007/s00134-020-05965-z 32100061 PMC7210239 · DOI
  7. [7]Carney N, Totten AM, O’Reilly C, Ullman JS, Hawryluk GWJ, Bell MJ, et al. Guidelines for the management of severe traumatic brain injury, fourth edition. Neurosurgery [Internet]. 2016 [cited 2017 Oct 26]; Available from: www.neurosurgery-online.com 27654000
  8. [8]Newcombe VFJ Chow A The features of the typical traumatic brain injury patient in the ICU are changing: what will this mean for the intensivist ? Curr Opin Crit Care 2021 27 80 10.1097/MCC.0000000000000814 33534257 · DOI
  9. [10]Maas AIR Menon DK Steyerberg EW Citerio G Lecky F Manley GT Collaborative European neurotrauma effectiveness research in traumatic brain injury (CENTER-TBI): a prospective longitudinal observational study Neurosurgery 2015 76 67 80 10.1227/NEU.0000000000000575 25525693 · DOI
  10. [11]Tenovuo O Diaz-Arrastia R Goldstein LE Sharp DJ van der Naalt J Zasler ND Assessing the severity of traumatic brain injury—time for a change? J Clin Med 2021 10 1 148 10.3390/jcm10010148 PMC7795933 33406786 · DOI
  11. [12]Kuruvilla ME Lee FEH Lee GB Understanding asthma phenotypes, endotypes, and mechanisms of disease Clin Rev Allergy Immunol 2019 56 2 219 233 10.1007/s12016-018-8712-1 30206782 PMC6411459 · DOI
  12. [13]Prescott HC Calfee CS Taylor Thompson B Angus DC Liu VX Toward smarter lumping and smarter splitting: rethinking strategies for sepsis and acute respiratory distress syndrome clinical trial design Am J Respir Crit Care Med 2016 194 2 147 155 10.1164/rccm.201512-2544CP 27244481 PMC5003218 · DOI
  13. [14]Calfee CS Delucchi K Parsons PE Thompson BT Ware LB Matthay MA Latent class analysis of ARDS subphenotypes: analysis of data from two randomized controlled trials Lancet Respir Med 2014 2 611 620 10.1016/S2213-2600(14)70097-9 24853585 PMC4154544 · DOI
  14. [15]Antcliffe DB Burnham KL Al-Beidh F Santhakumaran S Brett SJ Hinds CJ Transcriptomic signatures in sepsis and a differential response to steroids. From the VANISH randomized trial Am J Respir Crit Care Med 2019 199 8 980 986 10.1164/rccm.201807-1419OC 30365341 PMC6467319 · DOI
  15. [16]Steyerberg EW, Mushkudiani N, Perel P, Butcher I, Lu J, Mchugh GS, et al. Predicting outcome after traumatic brain injury: development and international validation of prognostic scores based on admission characteristics. 2008 [cited 2018 May 24]; Available from: http://journals.plos.org/plosmedicine/article/file?id=10.1371/journal.pmed.0050165&type=printable PMC2494563 18684008 · DOI
  16. [21]Lange T Roth V Braun ML Buhmann JM Stability-based validation of clustering solutions Neural Comput 2004 16 6 1299 1323 10.1162/089976604773717621 15130251 · DOI
  17. [23]Hyam JA Welch CA Harrison DA Menon DK Case mix, outcomes and comparison of risk prediction models for admissions to adult, general and specialist critical care units for head injury: a secondary analysis of the ICNARC case mix programme database Crit Care 2006 10 Suppl 2 S2 10.1186/cc5066 PMC3226136 17352796 · DOI
  18. [24]Raj R Skrifvars MB Bendel S Selander T Kivisaari R Siironen J Predicting six-month mortality of patients with traumatic brain injury: usefulness of common intensive care severity scores Crit Care 2014 18 2 1 9 10.1186/cc13814 PMC4056363 24708781 · DOI
  19. [25]Folweiler KA Sandsmark DK Diaz-Arrastia R Cohen AS Masino AJ Unsupervised machine learning reveals novel traumatic brain injury patient phenotypes with distinct acute injury profiles and long-term outcomes J Neurotrauma 2020 1444 1431 1444 10.1089/neu.2019.6705 PMC7249479 32008422 · DOI
  20. [26]Gravesteijn BY Sewalt CA Ercole A Akerlund C Nelson D Maas AIR Toward a new multi-dimensional classification of traumatic brain injury: a collaborative european neurotrauma effectiveness research for traumatic brain injury study J Neurotrauma 2020 37 7 1002 1010 10.1089/neu.2019.6764 31672086 · DOI
  21. [27]Yuh EL Jain S Sun X Pisică D Harris MH Taylor SR Pathological computed tomography features associated with adverse outcomes after mild traumatic brain injury: A TRACK-TBI study with external validation in CENTER-TBI JAMA Neurol 2021 78 9 1137 1148 10.1001/jamaneurol.2021.2120 34279565 PMC8290344 · DOI
  22. [28]Maas AIR Hukkelhoven CWPM Marshall LF Steyerberg EW Prediction of outcome in traumatic brain injury with computed tomographic characteristics: a comparison between the computed tomographic classification and combinations of computed tomographic predictors Neurosurgery 2005 57 6 1173 1181 10.1227/01.NEU.0000186013.63046.6B 16331165 · DOI
  23. [29]Thelin EP Nelson DW Vehviläinen J Nyström H Kivisaari R Siironen J Evaluation of novel computerized tomography scoring systems in human traumatic brain injury: an observational, multicenter study PLoS Med 2017 14 8 1 19 10.1371/journal.pmed.1002368 PMC5542385 28771476 · DOI
  24. [30]Raj R Siironen J Skrifvars MB Hernesniemi J Kivisaari R Predicting outcome in traumatic brain injury: development of a novel computerized tomography classification system (Helsinki Computerized Tomography Score) Neurosurgery 2014 75 6 632 646 10.1227/NEU.0000000000000533 25181434 · DOI
  25. [31]Nelson DW Nyström H MacCallum RM Thornquist B Lilja A Bellander BM Extended analysis of early computed tomography scans of traumatic brain injured patients and relations to outcome J Neurotrauma 2010 27 1 51 64 10.1089/neu.2009.0986 19698072 · DOI
  26. [32]Lingsma HF Roozenbeek B Steyerberg EW Murray GD Maas AI Early prognosis in traumatic brain injury: from prophecies to predictions Lancet Neurol 2010 9 5 543 554 10.1016/S1474-4422(10)70065-X 20398861 · DOI
  27. [33]Hawryluk GWJ Aguilera S Buki A Bulger E Citerio G Cooper DJ A management algorithm for patients with intracranial pressure monitoring: the seattle international severe traumatic brain injury consensus conference (SIBICC) Intensive Care Med 2019 45 12 1783 1794 10.1007/s00134-019-05805-9 31659383 PMC6863785 · DOI

Authors
Åkerlund, C. A. I., Holst, A., Stocchetti, N., Steyerberg, E. W., Menon, D. K., Ercole, A., Nelson, D. W., the CENTER-TBI Participants and Investigators, Åkerlund, C., Amrein, K., Andelic, N., Andreassen, L., Anke, A., Antoni, A., Audibert, G., Azouvi, P., Azzolini, M. L., Bartels, R., Barzó, P., Beauvais, R., Beer, R., Bellander, B.-M., Belli, A., Benali, H., Berardino, M., Beretta, L., Blaabjerg, M., Bragge, P., Brazinova, A., Brinck, V., Brooker, J., Brorsson, C., Buki, A., Bullinger, M., Cabeleira, M., Caccioppola, A., Calappi, E., Calvi, M. R., Cameron, P., Lozano, G. C., Carbonara, M., Cavallo, S., Chevallard, G., Chieregato, A., Citerio, G., Clusmann, H., Coburn, M., Coles, J., Cooper, J. D., Correia, M., Čović, A., Curry, N., Czeiter, E., Czosnyka, M., DahyotFizelier, C., Dark, P., Dawes, H., De Keyser, V., Degos, V., Corte, F. D., Boogert, H. D., Depreitere, B., Đilvesi, Đ., Dixit, A., Donoghue, E., Dreier, J., Dulière, G., Ercole, A., Esser, P., Ezer, E., Fabricius, M., Feigin, V. L., Foks, K., Frisvold, S., Furmanov, A., Gagliardo, P., Galanaud, D., Gantner, D., Gao, G., George, P., Ghuysen, A., Giga, L., Glocker, B., Golubovic, J., Gomez, P. A., Gratz, J., Gravesteijn, B., Grossi, F., Gruen, R. L., Gupta, D., Haagsma, J. A., Haitsma, I., Helbok, R., Helseth, E., Horton, L., Huijben, J., Hutchinson, P. J., Jacobs, B., Jankowski, S., Jarrett, M., Jiang, J., Johnson, F., Jones, K., Karan, M., Kolias, A. G., Kompanje, E., Kondziella, D., Kornaropoulos, E., Koskinen, L., Kovács, N., Kowark, A., Lagares, A., Lanyon, L., Laureys, S., Lecky, F., Ledoux, D., Lefering, R., Legrand, V., Lejeune, A., Levi, L., Lightfoot, R., Lingsma, H., Maas, A. I. R., CastañoLeón, A. M., Maegele, M., Majdan, M., Manara, A., Manley, G., Martino, C., Maréchal, H., Mattern, J., McMahon, C., Melegh, B., Menon, D., Menovsky, T., Mikolic, A., Misset, B., Muraleedharan, V., Murray, L., Negru, A., Nelson, D., Newcombe, V., Nieboer, D., Nyirádi, J., Olubukola, O., Oresic, M., Ortolano, F., Palotie, A., Parizel, P. M., Payen, J., Perera, N., Perlbarg, V., Persona, P., Peul, W., Piippo-Karjalainen, A., Pirinen, M., Pisica, D., Ples, H., Polinder, S., Pomposo, I., Posti, J. P., Puybasset, L., Radoi, A., Ragauskas, A., Raj, R., Rambadagalla, M., Helmrich, I. R., Rhodes, J., Richardson, S., Richter, S., Ripatti, S., Rocka, S., Roe, C., Roise, O., Rosand, J., Rosenfeld, J. V., Rosenlund, C., Rosenthal, G., Rossaint, R., Rossi, S., Rueckert, D., Rusnák, M., Sahuquillo, J., Sakowitz, O., SanchezPorras, R., Sandor, J., Schäfer, N., Schmidt, S., Schoechl, H., Schoonman, G., Schou, R. F., Schwendenwein, E., Sewalt, C., Singh, R. D., Skandsen, T., Smielewski, P., Sorinola, A., Stamatakis, E., Stanworth, S., Stevens, R., Stewart, W., Steyerberg, E. W., Stocchetti, N., Sundström, N., Takala, R., Tamás, V., Tamosuitis, T., Taylor, M. S., Ao, B. T., Tenovuo, O., Theadom, A., Thomas, M., Tibboel, D., Timmers, M., Tolias, C., Trapani, T., Tudora, C. M., Unterberg, A., Vajkoczy, P., Vallance, S., Valeinis, E., Vámos, Z., van der Jagt, M., Van der Steen, G., van der Naalt, J., van Dijck, J. T. J. M., van Erp, I. A., van Essen, T. A., Van Hecke, W., van Heugten, C., Van Praag, D., van Veen, E., Vyvere, T. V., van Wijk, R. P. J., Vargiolu, A., Vega, E., Velt, K., Verheyden, J., Vespa, P. M., Vik, A., Vilcinis, R., Volovici, V., von Steinbüchel, N., Voormolen, D., Vulekovic, P., Wang, K. K. W., Whitehouse, D., Wiegers, E., Williams, G., Wilson, L., Winzeck, S., Wolf, S., Yang, Z., Ylén, P., Younsi, A., Zeiler, F. A., Zelinkova, V., Ziverte, A., & Zoerle, T.
Affiliations
  • KTH Royal Institute of Technology (SE)
  • University of Pecs (HU)
  • University Hospital of North Norway (NO)
  • Medical University of Vienna (AT)
  • Centre Hospitalier Régional et Universitaire de Nancy (FR)
  • Assistance Publique – Hôpitaux de Paris (FR)
  • IRCCS Ospedale San Raffaele (IT)
  • Radboud University Medical Center (NL)
  • University of Szeged (HU)
  • Innsbruck Medical University (AT)
  • Karolinska University Hospital (SE)
  • NIHR Surgical Reconstruction and Microbiology Research Centre (GB)
  • CTO Hospital (IT)
  • Odense University Hospital (DK)
  • Monash University (AU)
  • Umeå University (SE)
  • University Medical Center Hamburg-Eppendorf (DE)
  • University of Cambridge (GB)
  • Fondazione IRCCS Ca' Granda Ospedale Maggiore Policlinico (IT)
  • Hospital de Cruces (ES)
  • Azienda Socio Sanitaria Territoriale Grande Ospedale Metropolitano Niguarda (IT)
  • Azienda Ospedaliera San Gerardo (IT)
  • RWTH Aachen University (DE)
  • MRC Cognition and Brain Sciences Unit (GB)
  • Karolinska Institutet (SE)
  • University of Trnava (SK)
  • University Hospital Bonn (DE)
ORCID
Venue
Critical Care
Publisher
Springer Science and Business Media LLC
Published
2022-07-27
Volume
26
Issue
1
Pages
228-228
ISSN
1364-8535 (ISSN-L)
DOI
10.1186/s13054-022-04079-w
PMC
PMC9327174
OpenAlex
W4288723913
Cited by
93
References
30
Citations by year
2026: 20 · 2025: 20 · 2024: 28 · 2023: 19 · 2022: 4
FWCI
9.35
Type
journal article
Language
en
Open access
Licence
Locations
  • Critical Care (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • University of Birmingham Research Portal (University of Birmingham) (publishedVersion, cc-by)
  • Research Explorer (The University of Manchester) (publishedVersion, other-oa)
  • EUR Research Repository (Erasmus University Rotterdam) (publishedVersion, cc-by)
  • White Rose Research Online (University of Leeds, The University of Sheffield, University of York) (acceptedVersion)
  • Monash University Research Portal (Monash University) (submittedVersion, cc-by)
  • Archivio Istituzionale della Ricerca (Universita Degli Studi Di Milano) (submittedVersion, other-oa)
  • Leiden Repository (Leiden University) (submittedVersion, other-oa)
  • University of Debrecen Electronic Archive (University of Debrecen) (submittedVersion, cc-by)
  • KTUePubl (Repository of Kaunas University of Technology) (submittedVersion, other-oa)
  • Rare & Special e-Zone (The Hong Kong University of Science and Technology) (submittedVersion)
  • EUR Research Repository (Erasmus University Rotterdam) (submittedVersion, other-oa)
  • Data Archiving and Networked Services (DANS) (submittedVersion, cc-by)
  • KTH Publication Database DiVA (KTH Royal Institute of Technology) (submittedVersion, other-oa)
  • BOA (University of Milano-Bicocca) (submittedVersion, other-oa)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • Archivio Istituzionale della Ricerca - Università Vita-Salute San Raffaele (submittedVersion)
  • Lithuanian University of Health Sciences (submittedVersion, cc-by)
  • NORA - Norwegian Open Research Archives (submittedVersion, cc-by)
  • RWTH Publications (RWTH Aachen) (submittedVersion, other-oa)
  • University of Groningen research database (University of Groningen / Centre for Information Technology) (submittedVersion, cc-by)
  • Leiden Repository (Leiden University) (submittedVersion, cc-by)
  • Apollo (University of Cambridge) (submittedVersion, cc-by)
  • Apollo (cc-by)
  • Apollo
  • RWTH Publications (RWTH Aachen)
Funders
Karolinska Institute
Topics
  • Health Sciences › Medicine › Neurology › Traumatic Brain Injury and Neurovascular Disturbances
  • Health Sciences › Medicine › Epidemiology › Traumatic Brain Injury Research
  • Health Sciences › Medicine › Emergency Medicine › Trauma and Emergency Care Studies
Keywords
traumatic brain injury, endotypes, unsupervised clustering, probabilistic graphs, intensive care unit, metabolic stress, Glasgow Coma Scale, outcome prediction, mortality prediction, IMPACT model, blood lactate, base excess, CENTER-TBI
MeSH terms
Brain Injuries, Traumatic, Critical Care, Humans, Prognosis, Glasgow Coma Scale, Cluster Analysis

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review