{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T06:12:34Z","timestamp":1788415954252,"version":"build-2803163510"},"reference-count":29,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T00:00:00Z","timestamp":1788393600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100011828","name":"Guangxi Zhuang Autonomous Region Health and Family Planning Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011828","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Despite high recanalization rates after endovascular treatment (EVT) for acute ischemic stroke due to large vessel occlusion (AIS-LVO), 15%\u221220% of patients still die within 90 days. Existing prognostic models predominantly target functional disability rather than mortality, and rarely incorporate calibration, clinical utility, or interpretability. We aimed to develop and internally validate interpretable machine learning (ML) models for dynamic post-EVT in-hospital prediction of 90-day all-cause mortality in AIS-LVO patients with successful recanalization.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      We retrospectively enrolled 449 AIS-LVO patients with successful EVT (modified Thrombolysis in Cerebral Infarction grade 2b\u22123) at a nationally certified Advanced Stroke Center in Guangxi, southwestern China, between January 2022 and May 2025. Candidate predictors included baseline characteristics, admission laboratory indicators, procedural variables, and post-procedural complications available during hospitalization. Patients were randomly split 8:2 into training (\n                      <jats:italic>n<\/jats:italic>\n                      = 359) and independent test (\n                      <jats:italic>n<\/jats:italic>\n                      = 90) sets, stratified by 90-day mortality. Fifteen ML algorithms were optimized via Bayesian hyperparameter search with 5-fold cross-validation, and the top five underwent bootstrap optimism correction. Performance was evaluated across discrimination, calibration, clinical utility (decision curve analysis), and reclassification (NRI\/IDI). SHapley Additive exPlanations (SHAP) and permutation importance were applied for interpretability.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The 90-day mortality rate was 19.6% (88\/449). Random Forest achieved favorable overall test-set performance (AUC = 0.806; Brier score = 0.128; Hosmer\u2013Lemeshow\n                      <jats:italic>p<\/jats:italic>\n                      = 0.315), with positive net benefit across threshold probabilities of 0.10\u20130.60. SHAP analysis identified stroke-associated pneumonia, D-dimer, age, acute renal insufficiency, fasting blood glucose, NIHSS score, brain herniation, and symptomatic intracranial hemorrhage as top contributors, concordant with permutation importance. Compared with LR-LASSO, Random Forest showed comparable discrimination without significant reclassification improvement (NRI = \u22120.472; IDI = \u22120.067).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>A Random Forest-based ML model with an online calculator and SHAP-based interpretability supports dynamic in-hospital post-EVT mortality risk stratification, with complication predictors incorporated only after they clinically occur. Prospective external validation in geographically diverse multicenter cohorts is warranted.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fneur.2026.1878562","type":"journal-article","created":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T05:14:42Z","timestamp":1788412482000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Interpretable machine learning\u2013based prediction of 90-day mortality after endovascular treatment in acute large vessel occlusion stroke"],"prefix":"10.3389","volume":"17","author":[{"given":"Yuanfang","family":"Zhou","sequence":"first","affiliation":[{"name":"Department of Neurology, Hezhou People's Hospital","place":["Hezhou, Guangxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoxia","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Neurology, Baise People's Hospital","place":["Baise, Guangxi, China"]},{"name":"Youjiang Medical University for Nationalities","place":["Baise, Guangxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guokuan","family":"Feng","sequence":"additional","affiliation":[{"name":"Department of Neurology, Hezhou People's Hospital","place":["Hezhou, Guangxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuanhang","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Neurology, Hezhou People's Hospital","place":["Hezhou, Guangxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bao","family":"Liao","sequence":"additional","affiliation":[{"name":"Department of Neurology, Baise People's Hospital","place":["Baise, Guangxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,3]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1038\/s41572-019-0118-8","article-title":"Ischaemic stroke","volume":"5","author":"Campbell","year":"2019","journal-title":"Nat Rev Dis Primers."},{"key":"B2","doi-asserted-by":"publisher","first-page":"e316","DOI":"10.1161\/STR.0000000000000513","article-title":"2026 guideline for the early management of patients with acute ischemic stroke: a guideline from the American heart association\/American stroke association","volume":"57","author":"Prabhakaran","year":"2026","journal-title":"Stroke"},{"key":"B3","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1016\/S1474-4422(25)00356-4","article-title":"Endovascular thrombectomy for acute stroke: evolving eligibility criteria and adjunct therapies","volume":"25","author":"Glavan","year":"2026","journal-title":"Lancet Neurol."},{"key":"B4","doi-asserted-by":"publisher","first-page":"660","DOI":"10.1161\/STROKEAHA.117.020315","article-title":"First pass effect","volume":"49","author":"Zaidat","year":"2018","journal-title":"Stroke."},{"key":"B5","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1007\/s11910-025-01427-5","article-title":"Systemic comorbidities as modifiers of outcome after endovascular thrombectomy for acute ischemic stroke","volume":"25","author":"Bond","year":"2025","journal-title":"Curr Neurol Neurosci Rep."},{"key":"B6","doi-asserted-by":"publisher","first-page":"1723","DOI":"10.1016\/S0140-6736(16)00163-X","article-title":"Endovascular thrombectomy after large-vessel ischaemic stroke: a meta-analysis of individual patient data from five randomised trials","volume":"387","author":"Goyal","year":"2016","journal-title":"Lancet."},{"key":"B7","doi-asserted-by":"publisher","first-page":"704088","DOI":"10.3389\/fneur.2021.704088","article-title":"Multiple-factor analyses of futile recanalization in acute ischemic stroke patients treated with mechanical thrombectomy","volume":"12","author":"Pan","year":"2021","journal-title":"Front Neurol."},{"key":"B8","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1016\/S0140-6736(24)01820-8","article-title":"Endovascular therapy for acute vertebrobasilar occlusion (VERITAS): a systematic review and individual patient data meta-analysis","volume":"405","author":"Nogueira","year":"2025","journal-title":"Lancet."},{"key":"B9","doi-asserted-by":"publisher","first-page":"3541","DOI":"10.1161\/STROKEAHA.120.030287","article-title":"Multimodal predictive modeling of endovascular treatment outcome for acute ischemic stroke using machine-learning","volume":"51","author":"Brugnara","year":"2020","journal-title":"Stroke."},{"key":"B10","doi-asserted-by":"publisher","first-page":"1124","DOI":"10.1136\/neurintsurg-2020-016997","article-title":"Optimal thresholds to predict long-term outcome after complete endovascular recanalization in acute anterior ischemic stroke","volume":"13","author":"Neuberger","year":"2021","journal-title":"J NeuroIntervent Surg."},{"key":"B11","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1212\/WNL.0b013e31827b1ace","article-title":"Stroke prognostication using age and NIH stroke scale","volume":"80","author":"Saposnik","year":"2013","journal-title":"Neurology."},{"key":"B12","doi-asserted-by":"publisher","first-page":"783","DOI":"10.1136\/neurintsurg-2014-011351","article-title":"Pittsburgh response to endovascular therapy (PRE) score: optimizing patient selection for endovascular therapy for large vessel occlusion strokes","volume":"7","author":"Rangaraju","year":"2015","journal-title":"J NeuroIntervent Surg."},{"key":"B13","doi-asserted-by":"publisher","first-page":"3324","DOI":"10.1161\/STROKEAHA.113.001050","article-title":"Optimizing prediction scores for poor outcome after intra-arterial therapy in anterior circulation acute ischemic stroke","volume":"44","author":"Sarraj","year":"2013","journal-title":"Stroke."},{"key":"B14","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1038\/s41591-024-03425-5","article-title":"The TRIPOD-LLM reporting guideline for studies using large language models","volume":"31","author":"Gallifant","year":"2025","journal-title":"Nat Med."},{"key":"B15","doi-asserted-by":"publisher","first-page":"13782","DOI":"10.1038\/s41598-023-40411-2","article-title":"Development and validation of a machine learning-based prognostic risk stratification model for acute ischemic stroke","volume":"13","author":"Wang","year":"2023","journal-title":"Sci Rep."},{"key":"B16","doi-asserted-by":"publisher","first-page":"5986","DOI":"10.1038\/s41598-026-37159-w","article-title":"Machine learning for predicting functional outcomes in acute ischemic stroke: insights from a nationwide stroke registry","volume":"16","author":"Ko","year":"2026","journal-title":"Sci Rep."},{"key":"B17","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":"B18","doi-asserted-by":"publisher","first-page":"e078378","DOI":"10.1136\/bmj-2023-078378","article-title":"TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"Collins","year":"2024","journal-title":"BMJ."},{"key":"B19","doi-asserted-by":"publisher","first-page":"2379","DOI":"10.1161\/STROKEAHA.119.025411","article-title":"Predicting clinical outcomes of large vessel occlusion before mechanical thrombectomy using machine learning","volume":"50","author":"Nishi","year":"2019","journal-title":"Stroke."},{"key":"B20","doi-asserted-by":"publisher","first-page":"107093","DOI":"10.1016\/j.cmpb.2022.107093","article-title":"Combining machine learning with radiomics features in predicting outcomes after mechanical thrombectomy in patients with acute ischemic stroke","volume":"225","author":"Li","year":"2022","journal-title":"Comput Methods Programs Biomed."},{"key":"B21","doi-asserted-by":"publisher","first-page":"2348","DOI":"10.1093\/brain\/awaf013","article-title":"Prediction of tissue and clinical thrombectomy outcome in acute ischaemic stroke using deep learning","volume":"148","author":"von Braun","year":"2025","journal-title":"Brain"},{"key":"B22","doi-asserted-by":"publisher","first-page":"2335","DOI":"10.1161\/STROKEAHA.115.009617","article-title":"Diagnosis of stroke-associated pneumonia","volume":"46","author":"Smith","year":"2015","journal-title":"Stroke."},{"key":"B23","doi-asserted-by":"publisher","first-page":"1023475","DOI":"10.3389\/fneur.2023.1023475","article-title":"Risk factors for and outcomes of poststroke pneumonia in patients with acute ischemic stroke treated with mechanical thrombectomy","volume":"14","author":"Zhang","year":"2023","journal-title":"Front Neurol."},{"key":"B24","doi-asserted-by":"publisher","first-page":"775","DOI":"10.1038\/nrn1765","article-title":"Central nervous system injury-induced immune deficiency syndrome","volume":"6","author":"Meisel","year":"2005","journal-title":"Nat Rev Neurosci"},{"key":"B25","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1016\/j.neuint.2018.01.002","article-title":"Research progress in stroke-induced immunodepression syndrome (SIDS) and stroke-associated pneumonia (SAP)","volume":"114","author":"Liu","year":"2018","journal-title":"Neurochem Int."},{"key":"B26","doi-asserted-by":"publisher","first-page":"2145","DOI":"10.2147\/CIA.S496733","article-title":"Characteristics of mortality after endovascular thrombectomy in patients with acute ischemic stroke","volume":"19","author":"Wang","year":"2024","journal-title":"CIA."},{"key":"B27","doi-asserted-by":"publisher","first-page":"e70267","DOI":"10.1111\/cns.70267","article-title":"Emergency admission plasma d-dimer and prothrombin activity: novel predictors for clinical outcomes after thrombectomy in acute ischemic stroke with large artery occlusion","volume":"31","author":"Jiang","year":"2025","journal-title":"CNS Neurosci Ther."},{"key":"B28","doi-asserted-by":"publisher","first-page":"e034556","DOI":"10.1161\/JAHA.124.034556","article-title":"Detrimental effect of acute hyperglycemia on the outcomes of large ischemic region stroke","volume":"13","author":"Tanaka","year":"2024","journal-title":"JAHA"},{"key":"B29","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.jclinepi.2019.02.004","article-title":"systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models","volume":"110","author":"Christodoulou","year":"2019","journal-title":"J Clin Epidemiol."}],"container-title":["Frontiers in Neurology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2026.1878562\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T05:14:43Z","timestamp":1788412483000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2026.1878562\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,3]]},"references-count":29,"alternative-id":["10.3389\/fneur.2026.1878562"],"URL":"https:\/\/doi.org\/10.3389\/fneur.2026.1878562","relation":{},"ISSN":["1664-2295"],"issn-type":[{"value":"1664-2295","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,3]]},"article-number":"1878562"}}