{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T13:53:56Z","timestamp":1789480436689,"version":"build-2803163510"},"reference-count":27,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Cardio"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Mortality prediction in intensive care unit (ICU) patients with ischemic stroke complicated by intracranial artery stenosis or occlusion remains difficult. Conventional scoring systems often lack discriminatory power and fail to provide individualized risk estimates. Machine learning approaches have been increasingly explored to integrate diverse clinical features for prognostic modeling.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aims to develop and evaluate machine learning models for individualized mortality prediction in ICU patients with ischemic stroke associated with intracranial artery stenosis or occlusion.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n \n Using the Medical Information Mart for Intensive Care IV (MIMIC-IV) database, we conducted a retrospective cohort study including 5280 adult ICU patients identified through\n International Classification of Diseases, Ninth and Tenth Revision<\/jats:italic>\n (\n ICD-9\/10<\/jats:italic>\n ) codes. Mortality status was determined based on the presence of a recorded date of death (dod) in the MIMIC-IV database. Patients with a documented dod were classified as deceased, whereas those without a recorded dod were classified as nondeceased. The primary outcome was all-cause mortality as recorded in the MIMIC-IV database, defined by the presence of a documented dod. Patients were randomly split into training (n=3696, 70%) and testing (n=1584, 30%) cohorts. Missing value imputation, correlation reduction, and multistep supervised feature selection (gradient boosting, BorutaShap, recursive feature elimination with cross-validation, LassoCV, and chi-square analysis) were performed exclusively within the training set and subsequently applied to the test set, resulting in 35 retained predictive features. Eight machine learning models\u2014including light gradient boosting machine (LightGBM), Bagging (bootstrap aggregating), random forest, logistic regression, support vector machine, gradient boosting, adaptive boosting, and k-nearest neighbors\u2014were trained with hyperparameter optimization using RandomizedSearchCV. Model performance was evaluated using area under the curve, accuracy, recall, precision,\n F<\/jats:italic>\n 1<\/jats:sub>\n -score, and calibration curves. Shapley additive explanations were used for global and individual-level interpretability.\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n LightGBM, Bagging, and logistic regression demonstrated comparable discrimination, achieving an area under the curve of approximately 0.82\u20100.83 and accuracy above 73% on the independent test set. LightGBM demonstrated balanced performance (recall 0.70; precision 0.72) and good calibration. Shapley additive explanations analysis identified acute physiology score III, suspected infection, Charlson comorbidity index, age, weight on admission, and red cell distribution width as the most influential predictors. Overall, higher physiological severity, greater comorbidity burden, and older age were consistently associated with increased observed mortality risk.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n Machine learning models\u2014including LightGBM and Bagging\u2014provide interpretable predictions of all-cause mortality in ICU patients with ischemic stroke and intracranial arterial disease. These models highlight key prognostic features and may support mortality risk stratification. External validation and evaluation of workflow integration are warranted before clinical implementation.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/82042","type":"journal-article","created":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T20:53:01Z","timestamp":1771966381000},"page":"e82042-e82042","source":"Crossref","is-referenced-by-count":4,"title":["Machine Learning Models for Mortality Prediction in Intensive Care Unit Patients With Ischemic Stroke Associated With Intracranial Artery Stenosis: Retrospective Cohort Study"],"prefix":"10.2196","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9408-1988","authenticated-orcid":false,"given":"Kun","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9018-930X","authenticated-orcid":false,"given":"Ruomeng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4264-9455","authenticated-orcid":false,"given":"Jingyi","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3416-4460","authenticated-orcid":false,"given":"Yan","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1398-5681","authenticated-orcid":false,"given":"Lijuan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6275-3299","authenticated-orcid":false,"given":"Chaoyue","family":"Meng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9318-9468","authenticated-orcid":false,"given":"Peifang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4850-4062","authenticated-orcid":false,"given":"Guoying","family":"Xing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8604-904X","authenticated-orcid":false,"given":"Xiaoyun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,2,24]]},"reference":[{"issue":"1","key":"R1","doi-asserted-by":"publisher","first-page":"3442","DOI":"10.1038\/s41598-020-60399-3","article-title":"Subtypes of anterior circulation large artery occlusions with acute brain ischemic stroke","volume":"10","author":"Zhang","journal-title":"Sci Rep"},{"issue":"6","key":"R2","doi-asserted-by":"publisher","first-page":"107714","DOI":"10.1016\/j.jstrokecerebrovasdis.2024.107714","article-title":"Differentiating ischemic stroke patients from healthy subjects using a large-scale, retrospective EEG database and machine learning methods","volume":"33","author":"Peterson","journal-title":"J Stroke Cerebrovasc Dis"},{"issue":"1","key":"R3","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-81980-0","article-title":"Prediction of prolonged mechanical ventilation in the intensive care unit via machine learning: a COVID-19 perspective","volume":"14","author":"Weaver","journal-title":"Sci Rep"},{"issue":"7","key":"R4","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0235424","article-title":"Benchmarking machine learning models on multi-centre eICU critical care dataset","volume":"15","author":"Sheikhalishahi","journal-title":"PLoS One"},{"key":"R5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jns.2022.120529","article-title":"Stroke mortality prediction using machine learning: systematic review","volume":"444","author":"Schwartz","journal-title":"J Neurol Sci"},{"issue":"1","key":"R6","doi-asserted-by":"publisher","first-page":"687","DOI":"10.1007\/s13042-024-02279-0","article-title":"Condensed-gradient boosting","volume":"16","author":"Emami","journal-title":"Int J Mach Learn & Cyber"},{"key":"R7","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2023.1254417","article-title":"Role of artificial intelligence and machine learning in the diagnosis of cerebrovascular disease","volume":"17","author":"Gilotra","journal-title":"Front Hum Neurosci"},{"key":"R8","doi-asserted-by":"publisher","DOI":"10.2196\/44895","article-title":"The value of applying machine learning in predicting the time of symptom onset in stroke patients: systematic review and meta-analysis","volume":"25","author":"Feng","journal-title":"J Med Internet Res"},{"issue":"1","key":"R9","doi-asserted-by":"publisher","DOI":"10.2196\/46840","article-title":"Predictive performance of machine learning-based models for poststroke clinical outcomes in comparison with conventional prognostic scores: multicenter, hospital-based observational study","volume":"3","author":"Irie","journal-title":"JMIR AI"},{"issue":"8","key":"R10","doi-asserted-by":"publisher","first-page":"2343","DOI":"10.1007\/s11517-024-03073-4","article-title":"Predicting ischemic stroke patients\u2019 prognosis changes using machine learning in a nationwide stroke registry","volume":"62","author":"Lin","journal-title":"Med Biol Eng Comput"},{"key":"R11","doi-asserted-by":"publisher","DOI":"10.2196\/59711","article-title":"A 25-year retrospective of the use of AI for diagnosing acute stroke: systematic review","volume":"26","author":"Wang","journal-title":"J Med Internet Res"},{"key":"R12","doi-asserted-by":"publisher","DOI":"10.2196\/71654","article-title":"Early predictive accuracy of machine learning for hemorrhagic transformation in acute ischemic stroke: systematic review and meta-analysis","volume":"27","author":"Wang","journal-title":"J Med Internet Res"},{"key":"R13","doi-asserted-by":"publisher","DOI":"10.1155\/srat\/3561616","article-title":"Dynamic, interpretable, machine learning-based outcome prediction as a new emerging opportunity in acute ischemic stroke patient care: a proof-of-concept study","volume":"2025","author":"Petrovi\u0107","journal-title":"Stroke Res Treat"},{"issue":"1","key":"R14","doi-asserted-by":"publisher","first-page":"28602","DOI":"10.1038\/s41598-025-09322-2","article-title":"Development and interpretation of a machine learning risk prediction model for post-stroke depression in a Chinese population","volume":"15","author":"Zhong","journal-title":"Sci Rep"},{"issue":"2","key":"R15","doi-asserted-by":"publisher","first-page":"106942","DOI":"10.1016\/j.jstrokecerebrovasdis.2022.106942","article-title":"Frailty and outcomes in lacunar stroke","volume":"32","author":"Vazquez","journal-title":"J Stroke Cerebrovasc Dis"},{"issue":"5","key":"R16","doi-asserted-by":"publisher","first-page":"1233","DOI":"10.1002\/ncp.10790","article-title":"Association of risk of malnutrition with adverse outcomes and early support on discharge in acute stroke patients without prestroke disability: a multicenter, registry-based cohort study","volume":"37","author":"Fluck","journal-title":"Nutr Clin Pract"},{"issue":"1","key":"R17","doi-asserted-by":"publisher","DOI":"10.1186\/s12877-022-02960-5","article-title":"Prevalence of dysphagia and risk of pneumonia and mortality in acute stroke patients: a meta-analysis","volume":"22","author":"Banda","journal-title":"BMC Geriatr"},{"issue":"11","key":"R18","doi-asserted-by":"publisher","first-page":"3137","DOI":"10.1016\/j.jstrokecerebrovasdis.2018.07.001","article-title":"Effectiveness and safety of antibiotics for preventing pneumonia and improving outcome after acute stroke: systematic review and meta-analysis","volume":"27","author":"Badve","journal-title":"J Stroke Cerebrovasc Dis"},{"issue":"2","key":"R19","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1136\/neurintsurg-2020-017066","article-title":"Age-adjusted infarct volume cut-off points improve stroke outcome prognostication beyond modeling with age and infarct volume","volume":"14","author":"Bouslama","journal-title":"J NeuroIntervent Surg"},{"key":"R20","doi-asserted-by":"publisher","DOI":"10.34172\/ijhpm.2021.79","article-title":"Length of stay, hospital costs and mortality associated with comorbidity according to the Charlson Comorbidity Index in immobile patients after ischemic stroke in China: a national study","volume":"11","author":"Liu","journal-title":"Int J Health Policy Manag"},{"issue":"8","key":"R21","doi-asserted-by":"publisher","DOI":"10.1161\/JAHA.124.040032","article-title":"Collateral circulation and rabep2 polymorphisms in large artery occlusion: impacts on short- and long-term prognosis","volume":"14","author":"Zhang","journal-title":"J Am Heart Assoc"},{"key":"R22","doi-asserted-by":"publisher","DOI":"10.3389\/fneur.2022.1009253","article-title":"Lactate-to-albumin ratio is associated with in-hospital mortality in patients with spontaneous subarachnoid hemorrhage and a nomogram model construction","volume":"13","author":"Zhang","journal-title":"Front Neurol"},{"issue":"10","key":"R23","doi-asserted-by":"publisher","first-page":"3156","DOI":"10.1161\/STROKEAHA.120.030429","article-title":"Infection as a stroke risk factor and determinant of outcome after stroke","volume":"51","author":"Elkind","journal-title":"Stroke"},{"issue":"9","key":"R24","doi-asserted-by":"publisher","first-page":"1780","DOI":"10.34172\/ijhpm.2021.79","article-title":"Length of stay, hospital costs and mortality associated with comorbidity according to the Charlson comorbidity index in immobile patients after ischemic stroke in China: a national study","volume":"11","author":"Liu","journal-title":"Int J Health Policy Manag"},{"issue":"1","key":"R25","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-024-02547-7","article-title":"A novel higher performance nomogram based on explainable machine learning for predicting mortality risk in stroke patients within 30 days based on clinical features on the first day ICU admission","volume":"24","author":"Chen","journal-title":"BMC Med Inform Decis Mak"},{"key":"R26","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2023.105049","article-title":"Machine learning prediction models and nomogram to predict the risk of in-hospital death for severe DKA: a clinical study based on MIMIC-IV, eICU databases, and a college hospital ICU","volume":"174","author":"Xie","journal-title":"Int J Med Inform"},{"key":"R27","doi-asserted-by":"publisher","DOI":"10.3389\/fneur.2023.1096153","article-title":"Analyzing and predicting the risk of death in stroke patients using machine learning","volume":"14","author":"Zhu","journal-title":"Front Neurol"}],"container-title":["JMIR Cardio"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/cardio.jmir.org\/2026\/1\/e82042","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:16:00Z","timestamp":1782843360000},"score":1,"resource":{"primary":{"URL":"https:\/\/cardio.jmir.org\/2026\/1\/e82042"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,24]]},"references-count":27,"URL":"https:\/\/doi.org\/10.2196\/82042","relation":{},"ISSN":["2561-1011"],"issn-type":[{"value":"2561-1011","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,24]]},"article-number":"v10i1e82042"}}