{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:04:33Z","timestamp":1792785873122,"version":"4.5.0"},"reference-count":33,"publisher":"Oxford University Press (OUP)","issue":"9","license":[{"start":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T00:00:00Z","timestamp":1789689600000},"content-version":"vor","delay-in-days":17,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"The Netherlands Brain Foundation","award":["HA2015.01.02"],"award-info":[{"award-number":["HA2015.01.02"]}]},{"name":"The Dutch Health Care Insurers Innovation Foundation","award":["3240"],"award-info":[{"award-number":["3240"]}]},{"name":"Health Holland","award":["LSHM16041-HOOB"],"award-info":[{"award-number":["LSHM16041-HOOB"]}],"id":[{"id":"https:\/\/ror.org\/056cwr036","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,5]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Adequate prehospital triage of anterior-circulation LVO (aLVO) or ICH enables direct allocation to appropriate stroke centres. Traditional triage based on clinical scales or logistic regression may miss complex predictor interactions, whereas machine learning approaches may improve diagnostic accuracy. We compared 3 prehospital triage methods to detect a composite outcome of aLVO or ICH using internal-external cross-validation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Patients and methods<\/jats:title>\n                    <jats:p>We analysed emergency medical services-activated stroke codes (2018-2019) from the Leiden Prehospital Stroke Study and the Prehospital Triage of Patients With Suspected Stroke Study. We compared XGBoost (supervised machine learning [sML]), conventional logistic regression (cLR) and the Rapid Arterial oCclusion Evaluation (RACE) scale using 2-fold internal-external cross-validation. Two variable sets were evaluated: (1) routine prehospital variables (demographics, symptom duration, vital signs, glucose, neurological deficits) and (2) an extended set including medical history, anticoagulant use and point-of-care international normalised ratio. Discrimination and calibration were assessed using balanced accuracy, sensitivity, specificity, Brier scores and calibration plots.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among 3320 patients, 538 (16%) had aLVO or ICH. Using routine variables, mean balanced accuracy was 82.1% for sML, 79.0% for cLR and 74.5% for RACE (P\u00a0&amp;lt;\u00a0.01). With extended variables, performance improved to 84.4% for sML and 80.7% for cLR (P\u00a0&amp;lt;\u00a0.01). The sML model achieved the highest sensitivity (76.7%) and specificity (92.1%). Calibration was good for both models, although Brier scores were lower for cLR.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>XGBoost showed modestly higher discriminative performance than cLR or RACE, while cLR showed better calibration. These findings suggest that machine learning may improve prehospital classification in selected settings, but the absolute gains were limited and require further external validation and prospective implementation studies.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/esj\/aakag112","type":"journal-article","created":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T16:37:12Z","timestamp":1789749432000},"source":"Crossref","is-referenced-by-count":0,"title":["Machine learning versus conventional methods for prehospital detection of stroke due to large vessel occlusion or intracranial haemorrhage"],"prefix":"10.1093","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0588-7654","authenticated-orcid":false,"given":"Bjarty L","family":"Garcia","sequence":"first","affiliation":[{"name":"Department of Public Health and Primary Care, Leiden University Medical Center (LUMC) , Leiden ,","place":["The Netherlands"]},{"name":"Department of Mathematics, Vrije Universiteit Amsterdam , Amsterdam ,","place":["The Netherlands"]},{"name":"National eHealth Living Lab, Leiden University Medical Center (LUMC) , Leiden ,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luuk","family":"Dekker","sequence":"additional","affiliation":[{"name":"Department of Neurology, Haga Hospital , The Hague ,","place":["The Netherlands"]},{"name":"Department of Neurology, Leiden University Medical Center (LUMC) , Leiden ,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rene","family":"Bekker","sequence":"additional","affiliation":[{"name":"Department of Mathematics, Vrije Universiteit Amsterdam , Amsterdam ,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marieke J H","family":"Wermer","sequence":"additional","affiliation":[{"name":"Department of Neurology, Leiden University Medical Center (LUMC) , Leiden ,","place":["The Netherlands"]},{"name":"Department of Neurology, University Medical Center Groningen (UMCG) , Groningen ,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ellis S","family":"van Etten","sequence":"additional","affiliation":[{"name":"Department of Neurology, Leiden University Medical Center (LUMC) , Leiden ,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erik W","family":"van Zwet","sequence":"additional","affiliation":[{"name":"Department of Biomedical Data Sciences, Leiden University Medical Center (LUMC) , Leiden ,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jan","family":"Bosch","sequence":"additional","affiliation":[{"name":"Department of Research and Development, Regional Ambulance Services Hollands Midden (RAVHM) , Leiden ,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adriaan C G M","family":"van Es","sequence":"additional","affiliation":[{"name":"Department of Radiology, Leiden University Medical Center (LUMC) , Leiden ,","place":["The Netherlands"]},{"name":"Department of Neurology, Haaglanden Medical Center , The Hague ,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ido R","family":"van den Wijngaard","sequence":"additional","affiliation":[{"name":"Department of Neurology, Haaglanden Medical Center , The Hague ,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Loet M H","family":"Kloos","sequence":"additional","affiliation":[{"name":"Department of Neurology, Groene Hart Ziekenhuis , Gouda ,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leo A M","family":"Aerden","sequence":"additional","affiliation":[{"name":"Department of Neurology, Reinier de Graaf Gasthuis , Delft ,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Els L L M","family":"de Schryver","sequence":"additional","affiliation":[{"name":"Department of Neurology, Alrijne Ziekenhuis , Leiderdorp ,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Henk","family":"Kerkhoff","sequence":"additional","affiliation":[{"name":"Department of Neurology, Albert Schweitzer Ziekenhuis , Dordrecht ,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Diederik W J","family":"Dippel","sequence":"additional","affiliation":[{"name":"Department of Neurology, Erasmus MC University Medical Center , Rotterdam ,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jasper D","family":"Daems","sequence":"additional","affiliation":[{"name":"Department of Neurology, Erasmus MC University Medical Center , Rotterdam ,","place":["The Netherlands"]},{"name":"Department of Public Health, Erasmus MC University Medical Center , Rotterdam ,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kirsten R I S","family":"Dorresteijn","sequence":"additional","affiliation":[{"name":"Department of Neurology, Franciscus Gasthuis & Vlietland , Rotterdam ,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Niels H","family":"Chavannes","sequence":"additional","affiliation":[{"name":"Department of Public Health and Primary Care, Leiden University Medical Center (LUMC) , Leiden ,","place":["The Netherlands"]},{"name":"National eHealth Living Lab, Leiden University Medical Center (LUMC) , Leiden ,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bob","family":"Roozenbeek","sequence":"additional","affiliation":[{"name":"Department of Neurology, Erasmus MC University Medical Center , Rotterdam ,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2320-0932","authenticated-orcid":false,"given":"Nyika D","family":"Kruyt","sequence":"additional","affiliation":[{"name":"Department of Neurology, Leiden University Medical Center (LUMC) , Leiden ,","place":["The Netherlands"]},{"name":"University Neurovascular Center (UNVC) Leiden-Den Haag, Leiden University Medical Center (LUMC) , Leiden ,","place":["The Netherlands"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"family":"for the LPSS and PRESTO investigators","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,9,18]]},"reference":[{"key":"2026100602311975700_ref1","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1159\/000441085","article-title":"Update on the global burden of ischemic and hemorrhagic stroke in 2013: the GBD 2013 study","volume":"45","author":"Feigin","year":"2015","journal-title":"Neuroepidemiology"},{"key":"2026100602311975700_ref2","first-page":"480","article-title":"Acute ischemic stroke: current status and future directions","volume":"113","author":"French","year":"2016","journal-title":"Mo Med"},{"key":"2026100602311975700_ref3","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1161\/CIRCULATIONAHA.117.032600","article-title":"Time to endovascular treatment and outcome in acute ischemic stroke: MR CLEAN registry results","volume":"138","author":"Mulder","year":"2018","journal-title":"Circulation"},{"key":"2026100602311975700_ref4","doi-asserted-by":"publisher","first-page":"1862","DOI":"10.1056\/NEJMoa2314741","article-title":"Intensive ambulance-delivered blood-pressure reduction in hyperacute stroke","volume":"390","author":"Li","year":"2024","journal-title":"N Engl J Med"},{"key":"2026100602311975700_ref5","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1001\/jamaneurol.2024.0221","article-title":"Time to anticoagulation reversal and outcomes after intracerebral hemorrhage","volume":"81","author":"Sheth","year":"2024","journal-title":"JAMA Neurol"},{"key":"2026100602311975700_ref6","doi-asserted-by":"publisher","first-page":"1277","DOI":"10.1056\/NEJMoa2308440","article-title":"Trial of early minimally invasive removal of intracerebral hemorrhage","volume":"390","author":"Pradilla","year":"2024","journal-title":"N Engl J Med"},{"key":"2026100602311975700_ref7","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0000000000213570","article-title":"Prehospital large-vessel occlusion stroke detection scales","volume":"104","author":"Dekker","year":"2025","journal-title":"Neurology"},{"key":"2026100602311975700_ref8","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1001\/jamaneurol.2020.4418","article-title":"Comparison of prehospital scales for predicting large anterior vessel occlusion in the ambulance setting","volume":"78","author":"Nguyen","year":"2021","journal-title":"JAMA Neurol"},{"key":"2026100602311975700_ref9","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1016\/S1474-4422(20)30439-7","article-title":"Comparison of eight prehospital stroke scales to detect intracranial large-vessel occlusion in suspected stroke (PRESTO): a prospective observational study","volume":"20","author":"Duvekot","year":"2021","journal-title":"Lancet Neurol"},{"key":"2026100602311975700_ref10","doi-asserted-by":"publisher","first-page":"8697","DOI":"10.1038\/s41598-023-35894-y","article-title":"Non-linear association between body weight and functional outcome after acute ischemic stroke","volume":"13","author":"Wakisaka","year":"2023","journal-title":"Sci Rep"},{"key":"2026100602311975700_ref11","doi-asserted-by":"publisher","first-page":"842","DOI":"10.3390\/diagnostics13050842","article-title":"XGBoost-based simple three-item model accurately predicts outcomes of acute ischemic stroke","volume":"13","author":"Chung","year":"2023","journal-title":"Diagnostics (Basel)"},{"key":"2026100602311975700_ref12","doi-asserted-by":"publisher","first-page":"9420","DOI":"10.1038\/s41598-022-13636-w","article-title":"Neural network-based clustering model of ischemic stroke patients with a maximally distinct distribution of 1-year vascular outcomes","volume":"12","author":"Kim","year":"2022","journal-title":"Sci Rep"},{"key":"2026100602311975700_ref13","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1186\/1471-2288-14-137","article-title":"Modern modelling techniques are data hungry: a simulation study for predicting dichotomous endpoints","volume":"14","author":"Ploeg","year":"2014","journal-title":"BMC Med Res Methodol"},{"key":"2026100602311975700_ref14","doi-asserted-by":"publisher","first-page":"1508","DOI":"10.1161\/STROKEAHA.115.008804","article-title":"Design and validation of a prehospital scale to predict stroke severity: Cincinnati Prehospital Stroke Severity Scale","volume":"46","author":"Katz","year":"2015","journal-title":"Stroke"},{"key":"2026100602311975700_ref15","doi-asserted-by":"publisher","first-page":"2264","DOI":"10.1161\/STROKEAHA.107.508127","article-title":"A brief prehospital stroke severity scale identifies ischemic stroke patients harboring persisting large arterial occlusions","volume":"39","author":"Nazliel","year":"2008","journal-title":"Stroke"},{"key":"2026100602311975700_ref16","doi-asserted-by":"publisher","DOI":"10.1161\/SVIN.123.000947","article-title":"Prehospital triage of intracranial hemorrhage and anterior large-vessel occlusion ischemic stroke: value of the RACE","volume":"3","author":"Dekker","year":"2023","journal-title":"Stroke: Vasc Interv Neurol"},{"key":"2026100602311975700_ref17","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2023-078378","volume":"385","author":"Collins","year":"2024","journal-title":"BMJ"},{"key":"2026100602311975700_ref18","author":"Friedman","year":"2003"},{"key":"2026100602311975700_ref19","volume-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","author":"Chen","year":"2016"},{"key":"2026100602311975700_ref20","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1161\/STROKEAHA.113.003071","article-title":"Design and validation of a prehospital stroke scale to predict large arterial occlusion: the rapid arterial occlusion evaluation scale","volume":"45","author":"Perez de la Ossa","year":"2014","journal-title":"Stroke"},{"key":"2026100602311975700_ref21","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1016\/j.jclinepi.2015.04.005","article-title":"Prediction models need appropriate internal, internal-external, and external validation","volume":"69","author":"Steyerberg","year":"2016","journal-title":"J Clin Epidemiol"},{"key":"2026100602311975700_ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.nicl.2024.103638","article-title":"Predicting recovery following stroke: deep learning, multimodal data and feature selection using explainable AI","volume":"43","author":"White","year":"2024","journal-title":"Neuroimage Clin"},{"key":"2026100602311975700_ref23","doi-asserted-by":"publisher","DOI":"10.3389\/fneur.2023.1114360","article-title":"Machine learning-based prediction of clinical outcomes after first-ever ischemic stroke","volume":"14","author":"Fast","year":"2023","journal-title":"Front Neurol"},{"key":"2026100602311975700_ref24","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1097\/01.ede.0000147512.81966.ba","article-title":"Optimal cut-point and its corresponding Youden index to discriminate individuals using pooled blood samples","volume":"16","author":"Schisterman","year":"2005","journal-title":"Epidemiology"},{"key":"2026100602311975700_ref25","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1186\/1471-2288-13-91","article-title":"The McNemar test for binary matched-pairs data: mid-p and asymptotic are better than exact conditional","volume":"13","author":"Fagerland","year":"2013","journal-title":"BMC Med Res Methodol"},{"key":"2026100602311975700_ref26","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1002\/mpr.329","article-title":"Multiple imputation by chained equations: what is it and how does it work?","volume":"20","author":"Azur","year":"2011","journal-title":"Int J Methods Psychiatr Res"},{"key":"2026100602311975700_ref27","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316696","volume-title":"Multiple Imputation for Nonresponse in Surveys","author":"Rubin","year":"1987"},{"key":"2026100602311975700_ref28","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-16399-0","volume-title":"Clinical Prediction Models: A Practical Approach to Development, Validation, and Updating","author":"Steyerberg","year":"2019","edition":"2"},{"key":"2026100602311975700_ref29","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1080\/10903127.2020.1800877","article-title":"Simplified prehospital prediction rule to estimate the likelihood of 4 types of stroke: the 7-item Japan Urgent Stroke Triage (JUST-7) score","volume":"25","author":"Uchida","year":"2021","journal-title":"Prehosp Emerg Care"},{"key":"2026100602311975700_ref30","doi-asserted-by":"publisher","first-page":"370","DOI":"10.1007\/s12975-021-00937-x","article-title":"Development of machine learning models to predict probabilities and types of stroke at prehospital stage: the Japan Urgent Stroke Triage Score using machine learning (JUST-ML)","volume":"13","author":"Uchida","year":"2022","journal-title":"Transl Stroke Res"},{"key":"2026100602311975700_ref31","doi-asserted-by":"publisher","DOI":"10.1161\/JAHA.123.033298","article-title":"Systematic review and meta-analysis of prehospital machine learning scores as screening tools for early detection of large vessel occlusion in patients with suspected stroke","volume":"13","author":"Alobaida","year":"2024","journal-title":"J Am Heart Assoc"},{"key":"2026100602311975700_ref32","doi-asserted-by":"publisher","first-page":"2279","DOI":"10.1161\/STROKEAHA.123.042644","article-title":"Comparison of prehospital assessment by paramedics and in-hospital assessment by physicians in suspected stroke patients: results from 2 prospective cohort studies","volume":"54","author":"Dekker","year":"2023","journal-title":"Stroke"},{"key":"2026100602311975700_ref33","doi-asserted-by":"publisher","first-page":"1782","DOI":"10.1001\/jama.2022.4404","article-title":"Effect of direct transportation to thrombectomy-capable center vs local stroke center on neurological outcomes in patients with suspected large-vessel occlusion stroke in nonurban areas: the RACECAT randomized clinical trial","volume":"327","author":"P\u00e9rez de la Ossa","year":"2022","journal-title":"JAMA"}],"container-title":["European Stroke Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/esj\/article-pdf\/11\/9\/aakag112\/71226785\/aakag112.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/esj\/article-pdf\/11\/9\/aakag112\/71226785\/aakag112.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T06:31:25Z","timestamp":1791268285000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/esj\/article\/doi\/10.1093\/esj\/aakag112\/8817381"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":33,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2026,9,5]]}},"URL":"https:\/\/doi.org\/10.1093\/esj\/aakag112","relation":{},"ISSN":["2396-9873","2396-9881"],"issn-type":[{"value":"2396-9873","type":"print"},{"value":"2396-9881","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,9]]},"published":{"date-parts":[[2026,9]]},"article-number":"aakag112"}}