{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T19:22:44Z","timestamp":1792783364189,"version":"4.5.0"},"reference-count":15,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T00:00:00Z","timestamp":1791936000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T00:00:00Z","timestamp":1791936000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004359","name":"Vetenskapsr\u00e5det","doi-asserted-by":"publisher","award":["2022-06725"],"award-info":[{"award-number":["2022-06725"]}],"id":[{"id":"10.13039\/501100004359","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004359","name":"Vetenskapsr\u00e5det","doi-asserted-by":"publisher","award":["no. 2018-05973"],"award-info":[{"award-number":["no. 2018-05973"]}],"id":[{"id":"10.13039\/501100004359","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006353","name":"Kjell och M\u00e4rta Beijers Stiftelse","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006353","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Swedish state","award":["ALF agreement between the Swedish government"],"award-info":[{"award-number":["ALF agreement between the Swedish government"]}]},{"name":"Swedish state","award":["Uppsala county council"],"award-info":[{"award-number":["Uppsala county council"]}]},{"DOI":"10.13039\/100011199","name":"FP7 Ideas: European Research Council","doi-asserted-by":"publisher","award":["602150"],"award-info":[{"award-number":["602150"]}],"id":[{"id":"10.13039\/100011199","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Uppsala University","id":[{"id":"https:\/\/ror.org\/048a87296","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neurocrit Care"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Raised intracranial pressure is one of the most severe secondary insults after traumatic brain injury. Recognising physiological patterns before they progress to dangerous intracranial pressure elevations could enable preventive rather than reactive interventions. In our previous Uppsala single-centre study, an XGBoost machine learning model showed high discriminative performance for prediction of imminent intracranial pressure insults. The model identifies short-term physiological trajectories associated with imminent threshold crossing rather than predicting independent future clinical events. Whether these results are generalisable across centres is unknown. The aim was therefore to evaluate whether the XGBoost model trained on an Uppsala dataset maintains similar performance when applied to a multicentre TBI cohort\u00a0- The CENTER-TBI High-Resolution ICU cohort.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The XGBoost model trained on the Uppsala high frequency traumatic brain injury cohort was externally validated using data from the multicentre CENTER-TBI cohort. Minute-level averages of intracranial pressure and invasive arterial blood pressure were used to predict the onset of an intracranial pressure insult within 30\u00a0min on the basis of a 4h historical window. A bidirectional validation design was applied and performance was assessed using multiple metrics.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The cohorts comprised 602 patients from Uppsala and 255 patients from the CENTER-TBI database. When trained on the Uppsala cohort and tested on CENTER-TBI, the model achieved an area under the receiver operating characteristic curve (AUROC) of 97.4%, sensitivity of 93.8%, and specificity of 98.6%. Training on CENTER-TBI and testing on the Uppsala dataset yielded an AUROC of 96.1%, sensitivity of 81.2%, and specificity of 98.7%. Balanced accuracy exceeded 88% in both validation directions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The XGBoost model retained high performance under external multicentre validation, indicating that pre-insult physiological patterns preceding increased intracranial pressure are shared across cohorts. Differences in sensitivity between validation directions were observed and may reflect cohort characteristics or dataset size. These findings support the need for local evaluation before clinical implementation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s12028-026-02633-w","type":"journal-article","created":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T01:53:34Z","timestamp":1792029214000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Artificial Intelligence for Early Prediction of Intracranial Hypertension: From Single-Centre Development to Multicentre Validation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9106-7160","authenticated-orcid":false,"given":"Peter","family":"Galos","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ludvig","family":"Hult","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giuseppe","family":"Citerio","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anders","family":"Lew\u00e9n","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anders","family":"H\u00e5nell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas B.","family":"Sch\u00f6n","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Per","family":"Enblad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"name":"In collaboration with The CENTER-TBI High-Resolution ICU (HR ICU) Sub-Study Participants and Investigators","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Audny","family":"Anke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ronny","family":"Beer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo-Michael","family":"Bellander","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erta","family":"Beqiri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andras","family":"Buki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Manuel","family":"Cabeleira","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Carbonara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arturo","family":"Chieregato","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hans","family":"Clusmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Endre","family":"Czeiter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marek","family":"Czosnyka","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bart","family":"Depreitere","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ari","family":"Ercole","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shirin","family":"Frisvold","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raimund","family":"Helbok","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefan","family":"Jankowski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Kondziella","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lars-Owe","family":"Koskinen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ana","family":"Kowark","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David K.","family":"Menon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Geert","family":"Meyfroidt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kirsten","family":"Moeller","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Nelson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anna","family":"Piippo-Karjalainen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreea","family":"Radoi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arminas","family":"Ragauskas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rahul","family":"Raj","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan","family":"Rhodes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saulius","family":"Rocka","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rolf","family":"Rossaint","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan","family":"Sahuquillo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oliver","family":"Sakowitz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Smielewski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nino","family":"Stocchetti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nina","family":"Sundstr\u00f6m","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Riikka","family":"Takala","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tomas","family":"Tamosuitis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olli","family":"Tenovuo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Unterberg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Vajkoczy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessia","family":"Vargiolu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rimantas","family":"Vilcinis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefan","family":"Wolf","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander","family":"Younsi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Frederick A.","family":"Zeiler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,10,14]]},"reference":[{"issue":"11","key":"2633_CR1","doi-asserted-by":"publisher","first-page":"1004","DOI":"10.1016\/S1474-4422(22)00309-X","volume":"21","author":"AIR Maas","year":"2022","unstructured":"Maas AIR, Menon DK, Manley GT, et al. Traumatic brain injury: progress and challenges in prevention, clinical care, and research. Lancet Neurol. 2022;21(11):1004\u201360. https:\/\/doi.org\/10.1016\/S1474-4422(22)00309-X.","journal-title":"Lancet Neurol"},{"issue":"1","key":"2633_CR2","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1038\/s41591-021-01614-0","volume":"28","author":"P Rajpurkar","year":"2022","unstructured":"Rajpurkar P, Chen E, Banerjee O, et al. AI in health and medicine. Nat Med. 2022;28(1):31\u20138. https:\/\/doi.org\/10.1038\/s41591-021-01614-0.","journal-title":"Nat Med"},{"issue":"1","key":"2633_CR3","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1007\/s00701-025-06725-y","volume":"167","author":"M Palermo","year":"2025","unstructured":"Palermo M, D\u2019Arrigo S, Olivi A, et al. Machine learning models for predicting vasospasm following ruptured intracranial aneurysms: a systematic review and meta-analysis. Acta Neurochir (Wien). 2025;167(1):314. https:\/\/doi.org\/10.1007\/s00701-025-06725-y.","journal-title":"Acta Neurochir (Wien)"},{"key":"2633_CR4","doi-asserted-by":"publisher","DOI":"10.1177\/08977151251395740","author":"S Hinds","year":"2025","unstructured":"Hinds S, Robertson C, Chen J, et al. High-frequency physiological measures predict post-admission surgical intervention after severe traumatic brain injury. J Neurotrauma. 2025. https:\/\/doi.org\/10.1177\/08977151251395740.","journal-title":"J Neurotrauma"},{"key":"2633_CR5","doi-asserted-by":"publisher","unstructured":"Van Hal ST, Van Der Jagt M, Van Genderen ME, et al. Using artificial intelligence to predict intracranial hypertension in patients after traumatic brain injury: a systematic review. Neurocrit Care [Online ahead of print]; https:\/\/doi.org\/10.1007\/s12028-023-01910-2.","DOI":"10.1007\/s12028-023-01910-2"},{"key":"2633_CR6","doi-asserted-by":"publisher","DOI":"10.1089\/neu.2022.0201","author":"R McNamara","year":"2022","unstructured":"McNamara R, Meka S, Anstey J, et al. Development of traumatic brain injury associated intracranial hypertension prediction algorithms: a narrative review. J Neurotrauma. 2022. https:\/\/doi.org\/10.1089\/neu.2022.0201.","journal-title":"J Neurotrauma"},{"issue":"2","key":"2633_CR7","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1007\/s12028-024-02119-7","volume":"42","author":"P Galos","year":"2025","unstructured":"Galos P, Hult L, Zachariah D, et al. Machine learning based prediction of imminent ICP insults during neurocritical care of traumatic brain injury. Neurocrit Care. 2025;42(2):387\u201397. https:\/\/doi.org\/10.1007\/s12028-024-02119-7.","journal-title":"Neurocrit Care"},{"issue":"10","key":"2633_CR8","doi-asserted-by":"publisher","first-page":"923","DOI":"10.1016\/S1474-4422(19)30232-7","volume":"18","author":"EW Steyerberg","year":"2019","unstructured":"Steyerberg EW, Wiegers E, Sewalt C, et al. 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\u201334. https:\/\/doi.org\/10.1016\/S1474-4422(19)30232-7.","journal-title":"Lancet Neurol"},{"issue":"1","key":"2633_CR9","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1227\/NEU.0000000000001432","volume":"80","author":"N Carney","year":"2017","unstructured":"Carney N, Totten AM, O\u2019Reilly C, et al. Guidelines for the management of severe traumatic brain injury. Fourth Edition Neurosurg. 2017;80(1):6\u201315. https:\/\/doi.org\/10.1227\/NEU.0000000000001432.","journal-title":"Fourth Edition Neurosurg"},{"key":"2633_CR10","first-page":"471","volume":"12","author":"TP Howells","year":"1995","unstructured":"Howells TP, Jones PA, Piper IR, Souter MJ, Miller JD. Design of a research database for the study of secondary insults following head injury. J Neurotrauma. 1995;12:471.","journal-title":"J Neurotrauma"},{"key":"2633_CR11","doi-asserted-by":"publisher","DOI":"10.1007\/s10877-022-00820-6","author":"P Galos","year":"2022","unstructured":"Galos P, Nyholm L, Howells T, et al. Capturing of intracranial pressure treatment during neurointensive care in patients with acute brain injury using a novel tablet-based method. J Clin Monit Comput. 2022. https:\/\/doi.org\/10.1007\/s10877-022-00820-6.","journal-title":"J Clin Monit Comput"},{"key":"2633_CR12","volume-title":"Python 3 reference manual","author":"G Van Rossum","year":"2009","unstructured":"Van Rossum G, Drake FL. Python 3 reference manual. Scotts Valley, CA: CreateSpace; 2009."},{"issue":"1","key":"2633_CR13","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1007\/s00701-024-05929-y","volume":"166","author":"AC Riparbelli","year":"2024","unstructured":"Riparbelli AC, Capion T, M\u00f8ller K, et al. Critical ICP thresholds in relation to outcome: is 22 mmHg really the answer? Acta Neurochir (Wien). 2024;166(1):63. https:\/\/doi.org\/10.1007\/s00701-024-05929-y.","journal-title":"Acta Neurochir (Wien)"},{"key":"2633_CR14","volume-title":"Best practices guidelines: the management of traumatic brain injury","author":"American College of Surgeons Committee on Trauma","year":"2015","unstructured":"American College of Surgeons Committee on Trauma. Best practices guidelines: the management of traumatic brain injury. Chicago, IL: American College of Surgeons; 2015."},{"issue":"10","key":"2633_CR15","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","volume":"22","author":"SJ Pan","year":"2010","unstructured":"Pan SJ, Yang Q. A survey on transfer learning. IEEE Trans Knowl Data Eng. 2010;22(10):1345\u201359. https:\/\/doi.org\/10.1109\/TKDE.2009.191.","journal-title":"IEEE Trans Knowl Data Eng"}],"container-title":["Neurocritical Care"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12028-026-02633-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12028-026-02633-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12028-026-02633-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T01:53:36Z","timestamp":1792029216000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12028-026-02633-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,14]]},"references-count":15,"alternative-id":["2633"],"URL":"https:\/\/doi.org\/10.1007\/s12028-026-02633-w","relation":{},"ISSN":["1541-6933","1556-0961"],"issn-type":[{"value":"1541-6933","type":"print"},{"value":"1556-0961","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,14]]},"assertion":[{"value":"21 April 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 July 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 October 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no conflicts of interest, except G.C., who revieves grants and personal fees as Speakers\u2019 Bureau and Advisory Board member from Integra and NeurOptics, all outside the submitted work.","order":1,"name":"Ethics","label":"Conflicts of Interest","group":{"name":"EthicsHeading","label":"Ethics"}},{"value":"The CENTER-TBI study (EC grant 602150) has been conducted in accordance with all relevant laws of the EU if directly applicable or of direct effect and all relevant laws of the country where the recruiting sites were located, including but not limited to, the relevant privacy and data protection laws and regulations (the \u201cPrivacy Law\u201d), the relevant laws and regulations on the use of human materials and all relevant guidance relating to clinical studies from time to time in force including, but not limited to, the ICH Harmonised Tripartite Guideline for Good Clinical Practice (CPMP\/ICH\/135\/95) (\u201cICH GCP\u201d) and the World Medical Association Declaration of Helsinki entitled \u201cEthical Principles for Medical Research Involving Human Subjects\u201d. Informed consent by the patients and\/or the legal representative\/next of kin was obtained, accordingly to the local legislations, for all patients recruited in the Core Dataset of CENTER-TBI and documented in the e-CRF. Ethical approval was obtained for each recruiting site. The list of sites, Ethical Committees, approval numbers and approval dates can be found on the website:\n                      \n                      . Informed consent was obtained from all participants\/waived due to the retrospective design. This is a retrospective study and for this type of study, formal consent is not required. The study was approved for UHF-TBI data by the local and the Swedish National Ethical Review Authority. Informed consent was obtained from patient or from their next of kin if the patient was unable to provide consent. It was also approved to include patients treated during the study period from whom consent not had been possible to obtain, for example, from deceased patients or when relatives had not been possible to reach.","order":2,"name":"Ethics","label":"Ethical Approval\/Informed Consent","group":{"name":"EthicsHeading","label":"Ethics"}},{"value":"Artificial intelligence (AI) was used solely to create one figure.","order":3,"name":"Ethics","label":"Artifical Intelligence","group":{"name":"EthicsHeading","label":"Ethics"}}]}}