{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T06:04:47Z","timestamp":1781071487262,"version":"3.54.1"},"reference-count":49,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T00:00:00Z","timestamp":1781049600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurosci."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Acute branch atheromatous disease (BAD) is one of the leading contributors to morbidity and disability in Asia, and early neurological deterioration (END) is common in affected patients. This study aimed to establish machine learning models to predict the risk of END in patients without reperfusion therapy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Patients with acute BAD who did not receive reperfusion therapy were retrospectively enrolled. Core predictive features were selected by LASSO regression with bootstrap stability assessment, and we used seven machine learning algorithms to build models. XGBoost was selected based on validation performance, nested cross-validation, and 1,000-iteration bootstrap validation. A spline logistic regression model served as the non-linear baseline. SHAP analysis was used to explain the model and develop a simple scoring system. Model discrimination was assessed using the area under the receiver operating characteristic curve (AUC), and clinical utility was evaluated using decision curve analysis (DCA).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>A total of 369 patients were included in our research. We screened predictive factors with LASSO regression and ultimately identified five key variables. These included maximum infarct area, lactate dehydrogenase (LDH), number of infarct slices, admission systolic blood pressure (SBP), and neutrophil count. The XGBoost model achieved the best overall performance, with AUC of 0.927 in the training set and 0.846 in the validation set. Nested cross-validation yielded an unbiased AUC of 0.866 (95% CI: 0.817\u20130.925), and bootstrap validation produced a mean OOB AUC of 0.855 (95% CI: 0.760\u20130.941). The scoring system stratified patients into low (0\u20136 points), intermediate (7\u201313 points), and high (14\u201320 points) risk groups. DCA demonstrated favorable clinical utility. SHAP analysis also indicated that maximum infarct area and LDH were the top two predictors of END.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>An XGBoost-based prediction model and a simple scoring system, integrating maximum infarct area, LDH, number of infarct slices, admission SBP, and neutrophil count, provide reliable END risk prediction for acute BAD patients without reperfusion therapy.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fnins.2026.1846221","type":"journal-article","created":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T05:40:06Z","timestamp":1781070006000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Predicting early neurological deterioration in acute branch atheromatous disease without reperfusion therapy: a machine learning model"],"prefix":"10.3389","volume":"20","author":[{"given":"Li","family":"Zeng","sequence":"first","affiliation":[{"name":"Department of Neurology, The First People\u2019s Hospital of Anqing Affiliated to Anhui Medical University","place":["Anqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"He","sequence":"additional","affiliation":[{"name":"Department of Neurology, The First People\u2019s Hospital of Anqing Affiliated to Anhui Medical University","place":["Anqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiuxiu","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Neurology, The First People\u2019s Hospital of Anqing Affiliated to Anhui Medical University","place":["Anqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liangbing","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Neurology, The First People\u2019s Hospital of Anqing Affiliated to Anhui Medical University","place":["Anqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,10]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1668420","DOI":"10.3389\/fneur.2025.1668420","article-title":"Evaluating machine learning models for stroke prediction based on clinical variables.","volume":"16","author":"Akinwumi","year":"2025","journal-title":"Front. Neurol."},{"key":"B2","doi-asserted-by":"publisher","first-page":"1678815","DOI":"10.3389\/fneur.2025.1678815","article-title":"Development and validation of explainable machine learning models for predicting 3-month functional outcomes in acute ischemic stroke: a SHAP-based approach.","volume":"16","author":"Chen","year":"2025","journal-title":"Front. Neurol."},{"key":"B3","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1186\/s12874-024-02331-1","article-title":"Predictive etiological classification of acute ischemic stroke through interpretable machine learning algorithms: a multicenter, prospective cohort study.","volume":"24","author":"Chen","year":"2024","journal-title":"BMC Med. Res. Methodol."},{"key":"B4","doi-asserted-by":"publisher","first-page":"2099","DOI":"10.1097\/hjh.0000000000000675","article-title":"Blood pressure variability and the development of early neurological deterioration following acute ischemic stroke.","volume":"33","author":"Chung","year":"2015","journal-title":"J. Hypertens."},{"key":"B5","doi-asserted-by":"publisher","first-page":"481","DOI":"10.1136\/svn-2024-003615","article-title":"Baseline systolic blood pressure and efficacy of dual antiplatelet in acute ischaemic stroke.","volume":"10","author":"Cui","year":"2025","journal-title":"Stroke Vasc. Neurol."},{"key":"B6","doi-asserted-by":"publisher","first-page":"4399","DOI":"10.2147\/jir.S317147","article-title":"Inflammatory factors as potential markers of early neurological deterioration in acute ischemic stroke patients receiving endovascular therapy - the AISRNA Study.","volume":"14","author":"Deng","year":"2021","journal-title":"J. Inflamm. Res."},{"key":"B7","doi-asserted-by":"publisher","first-page":"365","DOI":"10.15441\/ceem.24.220","article-title":"Short-term functional outcomes and treatment trends for branch atheromatous disease and lacunar infarction: a retrospective cohort study of a nationwide multicenter registry.","volume":"11","author":"Fujiwara","year":"2024","journal-title":"Clin. Exp. Emerg. Med."},{"key":"B8","doi-asserted-by":"publisher","first-page":"38","DOI":"10.4103\/aian.aian_883_24","article-title":"Predictive factors of early neurologic deterioration in isolated pontine infarction.","volume":"28","author":"Gao","year":"2025","journal-title":"Ann. Indian Acad. Neurol."},{"key":"B9","doi-asserted-by":"publisher","first-page":"1522868","DOI":"10.3389\/fneur.2025.1522868","article-title":"Interpretable prediction of stroke prognosis: SHAP for SVM and nomogram for logistic regression.","volume":"16","author":"Guo","year":"2025","journal-title":"Front. Neurol."},{"key":"B10","doi-asserted-by":"publisher","first-page":"1008","DOI":"10.1111\/jch.13310","article-title":"Blood pressures immediately following ischemic strokes are associated with cerebral perfusion and neurologic function.","volume":"20","author":"He","year":"2018","journal-title":"J. Clin. Hypertens."},{"key":"B11","doi-asserted-by":"publisher","first-page":"1450863","DOI":"10.3389\/fnagi.2024.1450863","article-title":"Mediation effect of stroke recurrence in the association between post-stroke lactate dehydrogenase and functional disability.","volume":"16","author":"He","year":"2024","journal-title":"Front. Aging Neurosci."},{"key":"B12","doi-asserted-by":"publisher","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":"B13","doi-asserted-by":"publisher","first-page":"1416","DOI":"10.5551\/jat.65653","article-title":"Hemostatic activation markers and early neurological deterioration in branch atheromatous disease-related stroke.","volume":"32","author":"Hoshino","year":"2025","journal-title":"J. Atheroscler. Thromb."},{"key":"B14","doi-asserted-by":"publisher","first-page":"1086339","DOI":"10.3389\/fpubh.2022.1086339","article-title":"Twenty-eight-day in-hospital mortality prediction for elderly patients with ischemic stroke in the intensive care unit: interpretable machine learning models.","volume":"10","author":"Huang","year":"2022","journal-title":"Front. Public Health"},{"key":"B15","doi-asserted-by":"publisher","first-page":"e14916","DOI":"10.1111\/cns.14916","article-title":"Brain border-derived CXCL2(+) neutrophils drive NET formation and impair vascular reperfusion following ischemic stroke.","volume":"30","author":"Huang","year":"2024","journal-title":"CNS Neurosci. Ther."},{"key":"B16","doi-asserted-by":"publisher","first-page":"17562864251357274","DOI":"10.1177\/17562864251357274","article-title":"Early intensive therapy for preventing neurological deterioration in branch atheromatous disease.","volume":"18","author":"Huang","year":"2025","journal-title":"Ther. Adv. Neurol. Disord."},{"key":"B17","doi-asserted-by":"publisher","first-page":"553326","DOI":"10.3389\/fneur.2020.553326","article-title":"The length of an infarcted lesion along the perforating artery predicts neurological deterioration in single subcortical infarction without any relevant artery stenosis.","volume":"11","author":"Jang","year":"2020","journal-title":"Front. Neurol."},{"key":"B18","doi-asserted-by":"publisher","first-page":"1496810","DOI":"10.3389\/fnins.2024.1496810","article-title":"A machine learning-based predictive model for predicting early neurological deterioration in lenticulostriate atheromatous disease-related infarction.","volume":"18","author":"Jiang","year":"2024","journal-title":"Front. Neurosci."},{"key":"B19","doi-asserted-by":"publisher","first-page":"816216","DOI":"10.3389\/fneur.2022.816216","article-title":"Elevated serum lactate dehydrogenase predicts unfavorable outcomes after rt-pa thrombolysis in ischemic stroke patients","volume":"13","author":"Jin","year":"2022","journal-title":"Front. Neurol."},{"key":"B20","doi-asserted-by":"publisher","first-page":"2488","DOI":"10.1038\/s41467-020-16191-y","article-title":"Neutrophil extracellular traps released by neutrophils impair revascularization and vascular remodeling after stroke.","volume":"11","author":"Kang","year":"2020","journal-title":"Nat. Commun."},{"key":"B21","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1159\/000450835","article-title":"Ultra-early combination antiplatelet therapy with cilostazol for the prevention of branch atheromatous disease: a multicenter prospective study.","volume":"6","author":"Kimura","year":"2016","journal-title":"Cerebrovasc. Dis. Extra"},{"key":"B22","doi-asserted-by":"publisher","first-page":"2025","DOI":"10.1161\/strokeaha.116.012901","article-title":"High-sensitive C-reactive protein predicts recurrent stroke and poor functional outcome: subanalysis of the clopidogrel in high-risk patients with acute nondisabling cerebrovascular events trial.","volume":"47","author":"Li","year":"2016","journal-title":"Stroke"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1390117","DOI":"10.3389\/fnins.2024.1390117","article-title":"Optimizing early neurological deterioration prediction in acute ischemic stroke patients following intravenous thrombolysis: a LASSO regression model approach.","volume":"18","author":"Li","year":"2024","journal-title":"Front. Neurosci."},{"key":"B24","doi-asserted-by":"publisher","first-page":"e70467","DOI":"10.1111\/cns.70467","article-title":"Association between argatroban and outcomes of branch atheromatous disease: a propensity-matched analysis from MRI-based study.","volume":"31","author":"Li","year":"2025","journal-title":"CNS Neurosci. Ther."},{"key":"B25","doi-asserted-by":"publisher","first-page":"2431","DOI":"10.1161\/strokeaha.124.047688","article-title":"Clinical and prognostic characteristics of acute BAD-related stroke: a multicenter MRI-based prospective study.","volume":"55","author":"Li","year":"2024","journal-title":"Stroke"},{"key":"B26","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1136\/svn-2022-002284","article-title":"Tirofiban combined with aspirin in the treatment of acute penetrating artery territory infarction (STRATEGY): protocol for a multicentre, randomised controlled trial.","volume":"9","author":"Liao","year":"2024","journal-title":"Stroke Vasc. Neurol."},{"key":"B27","doi-asserted-by":"publisher","first-page":"17562864221147743","DOI":"10.1177\/17562864221147743","article-title":"Early neurological deterioration in patients with acute ischemic stroke: a prospective multicenter cohort study.","volume":"16","author":"Liu","year":"","journal-title":"Ther. Adv. Neurol Disord."},{"key":"B28","doi-asserted-by":"publisher","first-page":"110689","DOI":"10.1016\/j.diabres.2023.110689","article-title":"Stress hyperglycemia predicts early neurological deterioration and poor outcomes in patients with single subcortical infarct.","volume":"200","author":"Liu","year":"","journal-title":"Diabetes Res. Clin. Pract."},{"key":"B29","doi-asserted-by":"publisher","first-page":"1368902","DOI":"10.3389\/fneur.2024.1368902","article-title":"Prediction of early neurologic deterioration in patients with perforating artery territory infarction using machine learning: a retrospective study.","volume":"15","author":"Liu","year":"2024","journal-title":"Front. Neurol."},{"key":"B30","doi-asserted-by":"publisher","first-page":"e3509","DOI":"10.1002\/brb3.3509","article-title":"Effect of mean platelet volume and platelet count on the prognosis of branch atheromatous disease","volume":"14","author":"Liu","year":"2024","journal-title":"Brain. Behav."},{"key":"B31","doi-asserted-by":"publisher","first-page":"108210","DOI":"10.1016\/j.jstrokecerebrovasdis.2024.108210","article-title":"Prognostic study of intracranial branch atheromatous disease in the blood-supplying areas of the lenticulostriate and paramedian pontine arteries.","volume":"34","author":"Liu","year":"2025","journal-title":"J. Stroke Cerebrovasc. Dis."},{"key":"B32","doi-asserted-by":"publisher","first-page":"912","DOI":"10.1161\/strokeaha.117.019440","article-title":"Boosted tree model reforms multimodal magnetic resonance imaging infarct prediction in acute stroke.","volume":"49","author":"Livne","year":"2018","journal-title":"Stroke"},{"key":"B33","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees.","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat. Mach. Intell."},{"key":"B34","doi-asserted-by":"publisher","first-page":"1662498","DOI":"10.3389\/fneur.2025.1662498","article-title":"A machine learning-based predictive nomogram for early neurological improvement after thrombolysis in acute ischemic stroke.","volume":"16","author":"Lv","year":"2025","journal-title":"Front. Neurol."},{"key":"B35","doi-asserted-by":"publisher","first-page":"e262","DOI":"10.1016\/s1470-2045(19)30149-4","article-title":"Big data and machine learning algorithms for health-care delivery.","volume":"20","author":"Ngiam","year":"2019","journal-title":"Lancet Oncol."},{"key":"B36","doi-asserted-by":"publisher","first-page":"e58021","DOI":"10.2196\/58021","article-title":"Machine learning-based explainable automated nonlinear computation scoring system for health score and an application for prediction of perioperative stroke: retrospective study.","volume":"27","author":"Oh","year":"2025","journal-title":"J. Med. Internet. Res."},{"key":"B37","doi-asserted-by":"publisher","first-page":"1373","DOI":"10.1016\/s0895-4356(96)00236-3","article-title":"A simulation study of the number of events per variable in logistic regression analysis.","volume":"49","author":"Peduzzi","year":"1996","journal-title":"J. Clin. Epidemiol."},{"key":"B38","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1038\/s41746-025-01687-y","article-title":"Hybrid machine learning for real-time prediction of edema trajectory in large middle cerebral artery stroke.","volume":"8","author":"Phillips","year":"2025","journal-title":"NPJ Digit. Med."},{"key":"B39","doi-asserted-by":"publisher","first-page":"e20588","DOI":"10.7717\/peerj.20588","article-title":"Integrating cerebrovascular morphology and radiomics features for predicting stroke prognosis: a retrospective study.","volume":"14","author":"Pu","year":"2026","journal-title":"PeerJ"},{"key":"B40","doi-asserted-by":"publisher","first-page":"13923","DOI":"10.1038\/s41598-025-98758-7","article-title":"Neutrophils induce astrocytic AQP4 expression via IL-1\u03b1 and TNF, contributing to cerebral oedema in ischaemic stroke rats.","volume":"15","author":"Sugimoto","year":"2025","journal-title":"Sci. Rep."},{"key":"B41","doi-asserted-by":"publisher","first-page":"3077","DOI":"10.1161\/strokeaha.119.026410","article-title":"NfL (Neurofilament Light Chain) levels as a predictive marker for long-term outcome after ischemic stroke.","volume":"50","author":"Uphaus","year":"2019","journal-title":"Stroke"},{"key":"B42","doi-asserted-by":"publisher","first-page":"581","DOI":"10.3389\/fneur.2020.00581","article-title":"Efficacy and safety of intravenous thrombolysis on acute branch atheromatous disease: a retrospective case-control study.","volume":"11","author":"Wu","year":"2020","journal-title":"Front. Neurol."},{"key":"B43","doi-asserted-by":"publisher","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":"B44","first-page":"1662","article-title":"Effect of argatroban plus dual antiplatelet in branch atherosclerosis disease: a randomized clinical trial.","volume":"56","author":"Xu","year":"2025","journal-title":"Stroke"},{"key":"B45","doi-asserted-by":"publisher","first-page":"10760296231221738","DOI":"10.1177\/10760296231221738","article-title":"Machine learning models for predicting early neurological deterioration and risk classification of acute ischemic stroke.","volume":"29","author":"Yang","year":"2023","journal-title":"Clin. Appl. Thromb. Hemost."},{"key":"B46","doi-asserted-by":"publisher","first-page":"11486","DOI":"10.1038\/s41598-023-37815-5","article-title":"Poststroke neutrophil count is predictive of the outcomes of large-artery atherosclerotic stroke and associated with craniocervical atherosclerosis.","volume":"13","author":"Yang","year":"2023","journal-title":"Sci. Rep."},{"key":"B47","doi-asserted-by":"publisher","first-page":"2705","DOI":"10.1161\/strokeaha.119.028287","article-title":"The incidence and associated factors of early neurological deterioration after thrombolysis: results from SITS registry.","volume":"51","author":"Yu","year":"2020","journal-title":"Stroke"},{"key":"B48","doi-asserted-by":"publisher","first-page":"e01922","DOI":"10.1002\/brb3.1922","article-title":"Inflammatory markers as independent predictors for stroke outcomes.","volume":"11","author":"Zhang","year":"2021","journal-title":"Brain Behav."},{"key":"B49","doi-asserted-by":"publisher","first-page":"1433010","DOI":"10.3389\/fneur.2024.1433010","article-title":"Predictors of early neurological deterioration in patients with acute ischemic stroke.","volume":"15","author":"Zhou","year":"2024","journal-title":"Front. Neurol."}],"container-title":["Frontiers in Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2026.1846221\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T05:40:09Z","timestamp":1781070009000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2026.1846221\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,10]]},"references-count":49,"alternative-id":["10.3389\/fnins.2026.1846221"],"URL":"https:\/\/doi.org\/10.3389\/fnins.2026.1846221","relation":{},"ISSN":["1662-453X"],"issn-type":[{"value":"1662-453X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,10]]},"article-number":"1846221"}}