{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T13:33:22Z","timestamp":1787924002892,"version":"build-2784847793"},"reference-count":25,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2025,12,13]],"date-time":"2025-12-13T00:00:00Z","timestamp":1765584000000},"content-version":"vor","delay-in-days":377,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Introduction:<\/jats:title>\n                    <jats:p>Formulating reliable prognosis for ischemic stroke patients remains a challenging task. We aimed to develop an artificial intelligence model able to formulate in the first 24\u2009h after stroke an individualized prognosis in terms of NIHSS.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Patients and methods:<\/jats:title>\n                    <jats:p>Seven hundred ninety four acute ischemic stroke patients were divided into a training (597) and testing (197) cohort. Clinical and instrumental data were collected in the first 24\u2009h. We evaluated the performance of four machine-learning models (Random Forest, K-Nearest Neighbors, Support Vector Machine, XGBoost) in predicting NIHSS at discharge both in terms of variation between discharge and admission (regressor approach) and in terms of severity class namely NIHSS 0\u20135, 6\u201310, 11\u201320, &amp;gt;20 (classifier approach). We used Shapley Additive exPlanations values to weight features impact on predictions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results:<\/jats:title>\n                    <jats:p>XGBoost emerged as the best performing model. The classifier and regressor approaches perform similarly in terms of accuracy (80% vs 75%) and f1-score (79% vs 77%) respectively. However, the regressor has higher precision (85% vs 68%) in predicting prognosis of very severe stroke patients (NIHSS\u2009&amp;gt;\u200920). NIHSS at admission and 24\u2009hours, GCS at 24\u2009hours, heart rate, acute ischemic lesion on CT-scan and TICI score were the most impacting features on the prediction.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion:<\/jats:title>\n                    <jats:p>Our approach, which employs an artificial intelligence based-tool, inherently able to continuously learn and improve its performance, could improve care pathway and support stroke physicians in the communication with patients and caregivers.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion:<\/jats:title>\n                    <jats:p>XGBoost reliably predicts individualized outcome in terms of NIHSS at discharge in the first 24\u2009hours after stroke.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1177\/23969873241253366","type":"journal-article","created":{"date-parts":[[2024,5,23]],"date-time":"2024-05-23T01:01:05Z","timestamp":1716426065000},"page":"1053-1062","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":15,"title":["Artificial intelligence to predict individualized outcome of acute ischemic stroke patients: The SIBILLA project"],"prefix":"10.1093","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1190-4879","authenticated-orcid":false,"given":"Pietro","family":"Caliandro","sequence":"first","affiliation":[{"name":"Unit of Neurology, Fondazione Policlinico Universitario A. Gemelli IRCCS, Rome, Italy 1"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jacopo","family":"Lenkowicz","sequence":"additional","affiliation":[{"name":"Real World Data Facility, Fondazione Policlinico Universitario A. Gemelli IRCCS, Rome, Italy 2"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giuseppe","family":"Reale","sequence":"additional","affiliation":[{"name":"Unit of High Intensity Neurorehabilitation, Fondazione Policlinico Universitario A. Gemelli IRCCS, Rome, Italy 3"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simone","family":"Scaringi","sequence":"additional","affiliation":[{"name":"Ammagamma s.r.l. Via Sant\u2019Orsola 33, Modena, Italy 4"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aurelia","family":"Zauli","sequence":"additional","affiliation":[{"name":"Unit of Neurology, Fondazione Policlinico Universitario A. Gemelli IRCCS, Rome, Italy 1"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Uccheddu","sequence":"additional","affiliation":[{"name":"Ammagamma s.r.l. Via Sant\u2019Orsola 33, Modena, Italy 4"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simone","family":"Fabiole-Nicoletto","sequence":"additional","affiliation":[{"name":"Ammagamma s.r.l. Via Sant\u2019Orsola 33, Modena, Italy 4"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefano","family":"Patarnello","sequence":"additional","affiliation":[{"name":"Real World Data Facility, Fondazione Policlinico Universitario A. Gemelli IRCCS, Rome, Italy 2"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrea","family":"Damiani","sequence":"additional","affiliation":[{"name":"Real World Data Facility, Fondazione Policlinico Universitario A. Gemelli IRCCS, Rome, Italy 2"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"Tagliaferri","sequence":"additional","affiliation":[{"name":"Unit of Radiotherapy, Fondazione Policlinico Universitario A. Gemelli IRCCS, Rome, Italy 5"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Iacopo","family":"Valente","sequence":"additional","affiliation":[{"name":"Unit of Interventional Neuroradiology, Fondazione Policlinico Universitario A. Gemelli IRCCS, Rome, Italy 6"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7893-1660","authenticated-orcid":false,"given":"Marco","family":"Moci","sequence":"additional","affiliation":[{"name":"Department of Neurosciences, Universit\u00e0 Cattolica del Sacro Cuore, Rome, Italy 7"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mauro","family":"Monforte","sequence":"additional","affiliation":[{"name":"Unit of Neurology, Fondazione Policlinico Universitario A. Gemelli IRCCS, Rome, Italy 1"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vincenzo","family":"Valentini","sequence":"additional","affiliation":[{"name":"Department of Oncology and Radiology, Ospedale Isola Tiberina-Gemelli Isola, Rome, Italy 8"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paolo","family":"Calabresi","sequence":"additional","affiliation":[{"name":"Unit of Neurology, Fondazione Policlinico Universitario A. Gemelli IRCCS, Rome, Italy 1"},{"name":"Department of Neurosciences, Universit\u00e0 Cattolica del Sacro Cuore, Rome, Italy 7"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2024,12,1]]},"reference":[{"key":"2026012113104127100_bibr1-23969873241253366","doi-asserted-by":"crossref","first-page":"1160","DOI":"10.1016\/S1474-4422(23)00277-6","article-title":"Pragmatic solutions to reduce the global burden of stroke: a world stroke organization-lancet neurology commission","volume":"22","author":"Feigin","year":"2023","journal-title":"Lancet Neurol"},{"key":"2026012113104127100_bibr2-23969873241253366","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1177\/2396987319883160","article-title":"Economic burden of stroke across Europe: a population-based cost analysis","volume":"5","author":"Luengo-Fernandez","year":"2020","journal-title":"Eur Stroke J"},{"key":"2026012113104127100_bibr3-23969873241253366","doi-asserted-by":"crossref","DOI":"10.1161\/STR.0000000000000211","article-title":"Guidelines for the early management of patients with acute ischemic stroke: 2019 update to the 2018 Guidelines for the early management of acute ischemic stroke: a guideline for healthcare professionals from the American heart association\/American stroke association","volume":"50","author":"Powers","year":"2019","journal-title":"Stroke"},{"key":"2026012113104127100_bibr4-23969873241253366","doi-asserted-by":"crossref","DOI":"10.1177\/2396987321989865","article-title":"European stroke organisation (ESO) guidelines on intravenous thrombolysis for acute ischaemic stroke","volume":"6","author":"Berge","year":"2021","journal-title":"Eur Stroke J"},{"key":"2026012113104127100_bibr5-23969873241253366","doi-asserted-by":"crossref","first-page":"611","DOI":"10.1056\/NEJMoa1804355","article-title":"MRI-guided thrombolysis for stroke with unknown time of onset","volume":"379","author":"Thomalla","year":"2018","journal-title":"New Engl J Med"},{"key":"2026012113104127100_bibr6-23969873241253366","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1111\/j.1747-4949.2011.00730.x","article-title":"A multicentre, randomized, Double-Blinded, placebo-controlled phase III study to investigate extending the time for thrombolysis in emergency neurological deficits (EXTEND)","volume":"7","author":"Ma","year":"2012","journal-title":"Int J Stroke"},{"key":"2026012113104127100_bibr7-23969873241253366","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1016\/S0140-6736(19)31053-0","article-title":"Extending thrombolysis to 4.5-9hours and wake-up stroke using perfusion imaging: a meta-analysis of individual patient data from EXTEND, ECASS4-EXTEND and EPITHET","volume":"394","author":"Campbell","year":"2019","journal-title":"Lancet"},{"key":"2026012113104127100_bibr8-23969873241253366","doi-asserted-by":"crossref","first-page":"708","DOI":"10.1056\/NEJMoa1713973","article-title":"Thrombectomy for stroke at 6 to 16 hours with selection by perfusion imaging","volume":"378","author":"Albers","year":"2018","journal-title":"New Engl J Med"},{"key":"2026012113104127100_bibr9-23969873241253366","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1056\/NEJMoa1706442","article-title":"Thrombectomy 6 to 24 hours after stroke with a mismatch between deficit and infarct","volume":"378","author":"Nogueira","year":"2018","journal-title":"N. Engl. J. Med"},{"key":"2026012113104127100_bibr10-23969873241253366","doi-asserted-by":"crossref","first-page":"2293","DOI":"10.1212\/WNL.0b013e31827a3c0a","article-title":"An integer-based score to predict functional outcome in acute ischemic stroke: the ASTRAL score","volume":"79","author":"Ntaios","year":"2012","journal-title":"Neurology"},{"key":"2026012113104127100_bibr11-23969873241253366","doi-asserted-by":"crossref","first-page":"1263","DOI":"10.1161\/STROKEAHA.118.024293","article-title":"Machine learning-based model for prediction of outcomes in acute stroke","volume":"50","author":"Heo","year":"2019","journal-title":"Stroke"},{"key":"2026012113104127100_bibr12-23969873241253366","doi-asserted-by":"crossref","DOI":"10.1016\/j.cmpb.2020.105381","article-title":"Evaluation of machine learning methods to stroke outcome prediction using a nationwide disease registry","volume":"190","author":"Lin","year":"2020","journal-title":"Comput Methods Programs Biomed"},{"key":"2026012113104127100_bibr13-23969873241253366","doi-asserted-by":"crossref","first-page":"44","DOI":"10.2214\/AJR.18.20260","article-title":"JOURNAL CLUB: use of gradient boosting machine learning to predict patient outcome in acute ischemic stroke on the basis of imaging, demographic, and clinical information","volume":"212","author":"Xie","year":"2019","journal-title":"AJR Am J Roentgenol"},{"key":"2026012113104127100_bibr14-23969873241253366","volume-title":"Springer series in statistics","author":"Friedman","year":"2001"},{"key":"2026012113104127100_bibr15-23969873241253366","volume-title":"Machine learning: A probabilistic perspective","author":"Murphy","year":"2012"},{"key":"2026012113104127100_bibr16-23969873241253366","doi-asserted-by":"crossref","first-page":"1920","DOI":"10.1161\/CIRCULATIONAHA.115.001593","article-title":"Machine learning in medicine","volume":"132","author":"Deo","year":"2015","journal-title":"Circulation"},{"key":"2026012113104127100_bibr17-23969873241253366","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1186\/s40537-019-0217-0","article-title":"Big data in healthcare: management, analysis and future prospects","volume":"6","author":"Dash","year":"2019","journal-title":"Big Data"},{"key":"2026012113104127100_bibr18-23969873241253366","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1002\/cpt.1907","article-title":"From real-world patient data to individualized treatment effects using machine learning: current and future methods to address underlying challenges","volume":"109","author":"Bica","year":"2021","journal-title":"Clin Pharmacol Ther"},{"key":"2026012113104127100_bibr19-23969873241253366","article-title":"Performance analysis of XGBoost classifier with missing data","author":"Aydin"},{"key":"2026012113104127100_bibr20-23969873241253366","doi-asserted-by":"crossref","first-page":"403","DOI":"10.5853\/jos.2020.02537","article-title":"Reliability and clinical utility of machine learning to predict stroke prognosis: comparison with logistic regression","volume":"22","author":"Jang","year":"2020","journal-title":"Stroke"},{"key":"2026012113104127100_bibr21-23969873241253366","doi-asserted-by":"crossref","first-page":"784","DOI":"10.3389\/fneur.2018.00784","article-title":"Predicting outcome of endovascular treatment for acute ischemic stroke: potential value of machine learning algorithms","volume":"9","author":"van Os","year":"2018","journal-title":"Front Neurol"},{"key":"2026012113104127100_bibr22-23969873241253366","doi-asserted-by":"crossref","first-page":"1761","DOI":"10.1161\/STROKEAHA.123.042496","article-title":"Deep learning versus neurologists: functional outcome prediction in LVO stroke patients undergoing mechanical thrombectomy","volume":"54","author":"Herzog","year":"2023","journal-title":"Stroke"},{"key":"2026012113104127100_bibr23-23969873241253366","doi-asserted-by":"crossref","first-page":"448","DOI":"10.1212\/WNL.0b013e31829d874e","article-title":"JURaSSiC: accuracy of clinician vs risk score prediction of ischemic stroke outcomes","volume":"81","author":"Saposnik","year":"2013","journal-title":"Neurology"},{"key":"2026012113104127100_bibr24-23969873241253366","doi-asserted-by":"crossref","DOI":"10.3389\/fneur.2021.727171","article-title":"Ordinal prediction model of 90-day modified rankin scale in ischemic stroke","volume":"12","author":"Zhang","year":"2021","journal-title":"Front Neurol"},{"key":"2026012113104127100_bibr25-23969873241253366","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1161\/STROKEAHA.119.026791","article-title":"National institutes of health stroke scale: an alternative primary outcome measure for trials of acute treatment for ischemic stroke","volume":"51","author":"Chalos","year":"2020","journal-title":"Stroke"}],"container-title":["European Stroke Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/23969873241253366","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/23969873241253366","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/academic.oup.com\/esj\/article-pdf\/9\/4\/1053\/64649857\/23969873241253366.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/esj\/article-pdf\/9\/4\/1053\/64649857\/23969873241253366.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T18:12:06Z","timestamp":1769019126000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/esj\/article\/9\/4\/1053\/8269083"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,1]]},"references-count":25,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,12,1]]}},"URL":"https:\/\/doi.org\/10.1177\/23969873241253366","relation":{},"ISSN":["2396-9873","2396-9881"],"issn-type":[{"value":"2396-9873","type":"print"},{"value":"2396-9881","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,12,1]]},"published":{"date-parts":[[2024,12,1]]}}}