A model for early detection of episodes of increased intracranial pressure in traumatic brain injury patients has been previously developed and validated based on retrospective adult patient data from the multicenter Brain-IT database. The purpose of the present study is to validate this early detection model in different cohorts of recently treated adult and pediatric traumatic brain injury patients.
Prognostic modeling. Noninterventional, observational, retrospective study.
The adult validation cohort comprised recent traumatic brain injury patients from San Gerardo Hospital in Monza (n = 50), Leuven University Hospital (n = 26), Antwerp University Hospital (n = 19), Tübingen University Hospital (n = 18), and Southern General Hospital in Glasgow (n = 8). The pediatric validation cohort comprised patients from neurosurgical and intensive care centers in Edinburgh and Newcastle (n = 79).
The model’s performance was evaluated with respect to discrimination, calibration, overall performance, and clinical usefulness. In the recent adult validation cohort, the model retained excellent performance as in the original study. In the pediatric validation cohort, the model retained good discrimination and a positive net benefit, albeit with a performance drop in the remaining criteria.
The obtained external validation results confirm the robustness of the model to predict future increased intracranial pressure events 30 minutes in advance, in adult and pediatric traumatic brain injury patients. These results are a large step toward an early warning system for increased intracranial pressure that can be generally applied. Furthermore, the sparseness of this model that uses only two routinely monitored signals as inputs (intracranial pressure and mean arterial blood pressure) is an additional asset.
1Department of Intensive Care Medicine, University Hospitals Leuven, Leuven, Belgium.
2Department of Neurosurgery, University Hospitals Leuven, Leuven, Belgium.
3Department of Clinical Physics, Southern General Hospital, Glasgow, United Kingdom.
4NeuroIntensive Care, Department of Emergency and Intensive Care, San Gerardo Hospital, Monza, Italy.
5Department of Intensive Care Medicine, Antwerp University Hospital, Edegem, Belgium.
6Department of Neurosurgery, Antwerp University Hospital, Edegem, Belgium.
7Department of Neurosurgery, Klinik für Neurochirurgie, Universitätsklinikum Tübingen, Tübingen, Germany.
8Department of Paediatric Intensive Care, Royal Hospital for Sick Children, Edinburgh, United Kingdom.
9School of Mathematics and Statistics, University of Glasgow, Glasgow, United Kingdom.
10Department of Paediatric Neurology, Royal Hospital for Sick Children, Edinburgh, United Kingdom.
Supported by the Foundation for Scientific Research Flanders (Fonds Wetenschappelijk Onderzoek - Vlaanderen [FWO]) (research project G. 0904.11). Brain-IT was funded by the European Framework Programme (FP5-QLRI-2000-00454, QLGT-2002-00160, and FP7-IST-2007–217049). The NEMO project in the University Hospital Edegem (Antwerp), Belgium, was funded by the Flemish Government Agency for Innovation by Science and Technology (IWT)—Applied Biomedical Research (TBM) program.
Dr. Depreitere’s institution received funding from the Johnson&Johnson educational grant. Dr. Piper received support for article research (EU Grants funded data collection of some of the data [Brain-IT data] upon which the project analyses were performed. FP5 QLGT-2002-00160 and FP7 IST-2007–217049). Dr. Citerio’s institution received funding from Educational activities for Codman. Dr. Maas’ institution received funding from the Framework 7 Program European Union and from IWT (Flemish agency for Innovation on Science and Technology). Dr. Jones received support for article research from Chief Scientist Office, Scotland, UK Brain-IT. Dr. Van den Berghe received long-term structural research financing via the Methusalem program funded by the Flemish Government (METH/08/07). Dr. Meyfroidt received funding from FWO as senior clinical investigator (1846113N). The remaining authors have disclosed that they do not have any potential conflicts of interest.
For information regarding this article, E-mail: firstname.lastname@example.org