Louis Puybasset1,2,3,4, Vincent Perlbarg5, Jean Unrug6,7, Didier Cassereau7, Damien Galanaud7,8, Grégory Torkomian6, Valentine Battisti6, Muriel Lefort7, Lionel Velly9,10, Vincent Degos11,12,13, Guiseppe Citerio14,15, Éléonore Bayen7,16, Mélanie Pelegrini-Issac7. 1. Neurosurgical Intensive Care Unit, APHP, Sorbonne Université, Hôpital Pitié-Salpêtrière, Paris, France. louis.puybasset@aphp.fr. 2. Laboratoire d'Imagerie Biomédicale (LIB), Sorbonne Université, CNRS, INSERM, Paris, France. louis.puybasset@aphp.fr. 3. Department of Anesthesiology and Intensive Care, Groupe Hospitalier Pitié-Salpêtrière, Assistance Publique-Hôpitaux de Paris, 47-83 Boulevard de l'Hôpital, 75013, Paris, France. louis.puybasset@aphp.fr. 4. Clinical Research Group 29, Sorbonne Université, Paris, France. louis.puybasset@aphp.fr. 5. BrainTale SAS, Paris, France. 6. Neurosurgical Intensive Care Unit, APHP, Sorbonne Université, Hôpital Pitié-Salpêtrière, Paris, France. 7. Laboratoire d'Imagerie Biomédicale (LIB), Sorbonne Université, CNRS, INSERM, Paris, France. 8. Department of Neuroradiology, APHP, Sorbonne Université, Hôpital Pitié-Salpêtrière, Paris, France. 9. Department of Anesthesiology and Critical Care Medicine, University Hospital Timone, AP-HM, Aix Marseille University, Marseille, France. 10. CNRS, Institute of Neuroscience Timone, UMR7289, Aix Marseille University, Marseille, France. 11. Clinical Research Group 29, Sorbonne Université, Paris, France. 12. Department of Anesthesia, Critical Care and Peri-Operative Medicine, APHP, Sorbonne Université, Hôpital Pitié-Salpêtrière, Paris, France. 13. INSERM UMR 1141, Paris, France. 14. Department of Medicine and Surgery, University of Milano-Bicocca, Monza, Italy. 15. Neurointensive Care Unit, Department of Emergency and Urgency, ASST-Monza, San Gerardo Hospital, Monza, Italy. 16. Rehabilitation Unit, APHP, Sorbonne Université, Hôpital Pitié-Salpêtrière, Paris, France.
Abstract
PURPOSE: A reliable tool for outcome prognostication in severe traumatic brain injury (TBI) would improve intensive care unit (ICU) decision-making process by providing objective information to caregivers and family. This study aimed at designing a new classification score based on magnetic resonance (MR) diffusion metrics measured in the deep white matter between day 7 and day 35 after TBI to predict 1-year clinical outcome. METHODS: Two multicenter cohorts (29 centers) were used. MRI-COMA cohort (NCT00577954) was split into MRI-COMA-Train (50 patients enrolled between 2006 and mid-2014) and MRI-COMA-Test (140 patients followed up in clinical routine from 2014) sub-cohorts. These latter patients were pooled with 56 ICU patients (enrolled from 2014 to 2020) from CENTER-TBI cohort (NCT02210221). Patients were dichotomised depending on their 1-year Glasgow outcome scale extended (GOSE) score: GOSE 1-3, unfavorable outcome (UFO); GOSE 4-8, favorable outcome (FO). A support vector classifier incorporating fractional anisotropy and mean diffusivity measured in deep white matter, and age at the time of injury was developed to predict whether the patients would be either UFO or FO. RESULTS: The model achieved an area under the ROC curve of 0.93 on MRI-COMA-Train training dataset, and 49% sensitivity for 96.8% specificity in predicting UFO and 58.5% sensitivity for 97.1% specificity in predicting FO on the pooled MRI-COMA-Test and CENTER-TBI validation datasets. CONCLUSION: The model successfully identified, with a specificity compatible with a personalized decision-making process in ICU, one in two patients who had an unfavorable outcome at 1 year after the injury, and two-thirds of the patients who experienced a favorable outcome.
PURPOSE: A reliable tool for outcome prognostication in severe traumatic brain injury (TBI) would improve intensive care unit (ICU) decision-making process by providing objective information to caregivers and family. This study aimed at designing a new classification score based on magnetic resonance (MR) diffusion metrics measured in the deep white matter between day 7 and day 35 after TBI to predict 1-year clinical outcome. METHODS: Two multicenter cohorts (29 centers) were used. MRI-COMA cohort (NCT00577954) was split into MRI-COMA-Train (50 patients enrolled between 2006 and mid-2014) and MRI-COMA-Test (140 patients followed up in clinical routine from 2014) sub-cohorts. These latter patients were pooled with 56 ICU patients (enrolled from 2014 to 2020) from CENTER-TBI cohort (NCT02210221). Patients were dichotomised depending on their 1-year Glasgow outcome scale extended (GOSE) score: GOSE 1-3, unfavorable outcome (UFO); GOSE 4-8, favorable outcome (FO). A support vector classifier incorporating fractional anisotropy and mean diffusivity measured in deep white matter, and age at the time of injury was developed to predict whether the patients would be either UFO or FO. RESULTS: The model achieved an area under the ROC curve of 0.93 on MRI-COMA-Train training dataset, and 49% sensitivity for 96.8% specificity in predicting UFO and 58.5% sensitivity for 97.1% specificity in predicting FO on the pooled MRI-COMA-Test and CENTER-TBI validation datasets. CONCLUSION: The model successfully identified, with a specificity compatible with a personalized decision-making process in ICU, one in two patients who had an unfavorable outcome at 1 year after the injury, and two-thirds of the patients who experienced a favorable outcome.
Authors: Andrew I R Maas; David K Menon; Ewout W Steyerberg; Giuseppe Citerio; Fiona Lecky; Geoffrey T Manley; Sean Hill; Valerie Legrand; Annina Sorgner Journal: Neurosurgery Date: 2015-01 Impact factor: 4.654
Authors: Benjamin Y Gravesteijn; Daan Nieboer; Ari Ercole; Hester F Lingsma; David Nelson; Ben van Calster; Ewout W Steyerberg Journal: J Clin Epidemiol Date: 2020-03-20 Impact factor: 6.437
Authors: Virginia Newcombe; Doris Chatfield; Joanne Outtrim; Sarah Vowler; Anne Manktelow; Justin Cross; Daniel Scoffings; Martin Coleman; Peter Hutchinson; Jonathan Coles; T Adrian Carpenter; John Pickard; Guy Williams; David Menon Journal: PLoS One Date: 2011-05-04 Impact factor: 3.240
Authors: Ewout W Steyerberg; Nino Mushkudiani; Pablo Perel; Isabella Butcher; Juan Lu; Gillian S McHugh; Gordon D Murray; Anthony Marmarou; Ian Roberts; J Dik F Habbema; Andrew I R Maas Journal: PLoS Med Date: 2008-08-05 Impact factor: 11.069