{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T11:09:47Z","timestamp":1788952187527,"version":"build-2803163510"},"reference-count":43,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T00:00:00Z","timestamp":1788912000000},"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. Med."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study seeks to develop and compare four machine learning models using the MIMIC-IV database to identify predictive variables associated with invasive mechanical ventilation (MV) requirement in patients with embolic cerebral infarction.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      This study included 568 patients with embolic cerebral infarction from the MIMIC-IV database. Data collected encompassed demographic information, vital signs, laboratory results, and other relevant variables. The dataset was randomly split into a development set and a validation set in a 7:3 ratio. Feature selection was performed using univariable and multivariable analyses. Four prediction models, namely decision tree (DT), logistic regression (LR), eXtreme Gradient Boosting (XGB), and Light Gradient Boosting Machine (LGBM), were developed. Model performance was assessed using receiver operating characteristic (ROC) curve analysis. Calibration was evaluated through calibration curves and Brier scores. Clinical utility was examined using decision curve analysis (DCA), and Shapley additive explanations (SHAP) were used to interpret model predictions. ICU admission was t\n                      <jats:sub>0<\/jats:sub>\n                      and predictors were summarized over the first 24 h. Because exact MV-initiation times were unavailable, robustness analyses addressed optimism, class imbalance, and temporal ambiguity using repeated nested cross-validation, an all-MV benchmark, inverse-frequency weighting, and exclusion of pneumonia and log input amount.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among 568 patients, 438 received invasive MV. XGB achieved an AUROC of 0.839 (95% CI, 0.796\u20130.883) in the development set and 0.720 (95% CI, 0.637\u20130.801) in the validation set; repeated nested cross-validation yielded 0.713 (95% CI, 0.665\u20130.757). The all-MV benchmark had a specificity of 0 and 0.500 balanced accuracy, whereas XGB achieved 0.700 and 0.659, respectively. Excluding pneumonia and log input amount reduced the nested-CV AUROC to 0.654 (95% CI, 0.595\u20130.703). SHAP analysis identified pneumonia, hematocrit, INR, weight, heart failure, log input amount, and glucose as the highest-importance features.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This study developed four machine learning models to assess the necessity of mechanical ventilation support in patients with embolic cerebral infarction and compared their performance. XGB showed the most favorable overall validation profile but requires time-stamped external validation before clinical use.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1945368","type":"journal-article","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T10:14:39Z","timestamp":1788948879000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Machine learning prediction models for mechanical ventilation requirement in patients with embolic stroke: a retrospective cohort study based on MIMIC-IV"],"prefix":"10.3389","volume":"13","author":[{"given":"Li","family":"Ma","sequence":"first","affiliation":[{"name":"Department of Oncology Surgery, Lanzhou University Second Hospital","place":["Lanzhou, Gansu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuhui","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Neurology, Lanzhou University Second Hospital","place":["Lanzhou, Gansu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruiling","family":"Nan","sequence":"additional","affiliation":[{"name":"Department of Neurology, Lanzhou University Second Hospital","place":["Lanzhou, Gansu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Yan","sequence":"additional","affiliation":[{"name":"Department of Nursing, Lanzhou University Second Hospital","place":["Lanzhou, Gansu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinglei","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Cardiology, Lanzhou University Second Hospital","place":["Lanzhou, Gansu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haixia","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Oncology Surgery, Lanzhou University Second Hospital","place":["Lanzhou, Gansu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinman","family":"Dou","sequence":"additional","affiliation":[{"name":"Department of Nursing, Lanzhou University Second Hospital","place":["Lanzhou, Gansu, China"]},{"name":"School of Nursing, Lanzhou University","place":["Lanzhou, Gansu, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xujie","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Emergency ICU, The Affiliated Hospital of Qinghai University","place":["Xining, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,9]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"2820","DOI":"10.1016\/S0140-6736(24)00642-1","article-title":"Stroke","volume":"403","author":"Hilkens","year":"2024","journal-title":"Lancet (London, England)"},{"key":"B2","doi-asserted-by":"publisher","first-page":"BSR20220995","DOI":"10.1042\/BSR20220995","article-title":"Identification of key predictors of hospital mortality in critically ill patients with embolic stroke using machine learning","volume":"42","author":"Liu","year":"2022","journal-title":"Biosci Rep"},{"key":"B3","doi-asserted-by":"publisher","first-page":"737","DOI":"10.1161\/STROKEAHA.124.048305","article-title":"Prevalence of high-risk CTA-based carotid plaque-RADS subtypes in patients with embolic stroke of undetermined source","volume":"56","author":"Song","year":"2025","journal-title":"Stroke"},{"key":"B4","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1007\/s00134-025-07808-1","article-title":"Ventilation practices in acute brain injured patients and association with outcomes: the VENTIBRAIN multicenter observational study","volume":"51","author":"Robba","year":"2025","journal-title":"Intensive Care Med"},{"key":"B5","doi-asserted-by":"publisher","first-page":"1351458","DOI":"10.3389\/fneur.2024.1351458","article-title":"Nomogram to predict ventilator-associated pneumonia in large vessel occlusion stroke after endovascular treatment: a retrospective study","volume":"15","author":"Zhu","year":"2024","journal-title":"Front Neurol"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1292","DOI":"10.1007\/s00134-025-08002-z","article-title":"Melatonin for prevention of delirium in patients receiving mechanical ventilation in the intensive care unit: a multiarm multistage adaptive randomized controlled clinical trial (DEMEL)","volume":"51","author":"Mekontso Dessap","year":"2025","journal-title":"Intensive Care Med"},{"key":"B7","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1186\/s13054-022-04290-9","article-title":"The sequential organ failure assessment (SOFA) score: has the time come for an update?","volume":"27","author":"Moreno","year":"2023","journal-title":"Critical Care (London. England)"},{"key":"B8","doi-asserted-by":"publisher","first-page":"434","DOI":"10.4187\/respcare.12317","article-title":"Treatment intensity and outcomes in elderly mechanically ventilated ICU patients","volume":"70","author":"Rosa","year":"2025","journal-title":"Respir Care"},{"key":"B9","doi-asserted-by":"publisher","first-page":"697","DOI":"10.20344\/amp.21435","article-title":"Logistic regression: limitations in the estimation of measures of association with binary health outcomes","volume":"37","author":"Pinheiro-Guedes","year":"2024","journal-title":"Acta Med Port"},{"key":"B10","doi-asserted-by":"publisher","first-page":"105049","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","year":"2023","journal-title":"Int J Med Inf"},{"key":"B11","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1186\/s13054-024-05138-0","article-title":"Interpretable machine learning model for new-onset atrial fibrillation prediction in critically ill patients: a multi-center study","volume":"28","author":"Guan","year":"2024","journal-title":"Critical care (London. England)"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41597-022-01899-x","article-title":"MIMIC-IV, a freely accessible electronic health record dataset","volume":"10","author":"Johnson","year":"2023","journal-title":"Sci Data"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1878","DOI":"10.1177\/1460458218810760","article-title":"The assessment of data quality issues for process mining in healthcare using medical information mart for intensive care III, a freely available e-health record database","volume":"25","author":"Kurniati","year":"2019","journal-title":"Health Informatics J"},{"key":"B14","doi-asserted-by":"publisher","first-page":"105887","DOI":"10.1016\/j.ijmedinf.2025.105887","article-title":"Comparing logistic regression and machine learning for obesity risk prediction: a systematic review and meta-analysis","volume":"199","author":"Boakye","year":"2025","journal-title":"Int J Med Inf"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1545979","DOI":"10.3389\/fcimb.2025.1545979","article-title":"Early prediction of sepsis associated encephalopathy in elderly ICU patients using machine learning models: a retrospective study based on the MIMIC-IV database","volume":"15","author":"Han","year":"2025","journal-title":"Front Cell Infect Microbiol"},{"key":"B16","doi-asserted-by":"publisher","first-page":"534","DOI":"10.1001\/jamapsychiatry.2019.3671","article-title":"Establishment of best practices for evidence for prediction: a review","volume":"77","author":"Poldrack","year":"2020","journal-title":"JAMA Psychiatry"},{"key":"B17","doi-asserted-by":"publisher","first-page":"18226","DOI":"10.1038\/s41598-022-22948-w","article-title":"Interpretable predictive model for shield attitude control performance based on XGB and SHAP","volume":"12","author":"Hu","year":"2022","journal-title":"Sci Rep"},{"key":"B18","doi-asserted-by":"publisher","first-page":"e533","DOI":"10.1212\/WNL.0000000000013127","article-title":"Association of the verbal component of the GCS with mortality in patients with encephalopathy who are not undergoing mechanical ventilation","volume":"98","author":"Selioutski","year":"2022","journal-title":"Neurology"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1435809","DOI":"10.3389\/fneur.2024.1435809","article-title":"Comparison and combined use of NEWS2 and GCS scores in predicting mortality in stroke and traumatic brain injury: a multicenter retrospective study","volume":"15","author":"Hu","year":"2024","journal-title":"Front Neurol"},{"key":"B20","doi-asserted-by":"publisher","first-page":"105874","DOI":"10.1016\/j.ijmedinf.2025.105874","article-title":"Development and validation of an interpretable machine learning model for predicting in-hospital mortality for ischemic stroke patients in ICU","volume":"198","author":"Luo","year":"2025","journal-title":"Int J Med Inf"},{"key":"B21","doi-asserted-by":"publisher","first-page":"348","DOI":"10.1007\/s12028-023-01674-9","article-title":"One-Year survival of ischemic stroke patients requiring mechanical ventilation","volume":"39","author":"Isokuortti","year":"2023","journal-title":"Neurocrit Care"},{"key":"B22","doi-asserted-by":"publisher","first-page":"420","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","year":"2022","journal-title":"BMC Geriatr"},{"key":"B23","doi-asserted-by":"publisher","first-page":"108593","DOI":"10.1016\/j.clineuro.2024.108593","article-title":"Risk factors for stroke-related pneumonia in patients with ischaemic stroke: a systematic evaluation and meta-analysis","volume":"246","author":"Li","year":"2024","journal-title":"Clin Neurol Neurosurg"},{"key":"B24","doi-asserted-by":"publisher","first-page":"518","DOI":"10.3390\/healthcare8040518","article-title":"Clinical characteristics of the COVID-19 patients with pneumonia detected by computerized tomography but negative for infiltration by x-ray","volume":"8","author":"Acharya","year":"2020","journal-title":"Healthcare (Basel, Switzerland)"},{"key":"B25","doi-asserted-by":"publisher","first-page":"1059","DOI":"10.1177\/0271678X241310780","article-title":"Association between cerebral oxygenation and usual parameters of cerebral perfusion in critically ill patients with acute brain injury","volume":"45","author":"Ayasse","year":"2025","journal-title":"J Cereb Blood Flow Metab"},{"key":"B26","doi-asserted-by":"publisher","first-page":"e207961","DOI":"10.1212\/WNL.0000000000207961","article-title":"Relationships of hematocrit with chronic covert and acute symptomatic lacunar ischemic lesions","volume":"102","author":"Roh","year":"2024","journal-title":"Neurology"},{"key":"B27","doi-asserted-by":"publisher","first-page":"123558","DOI":"10.1016\/j.jns.2025.123558","article-title":"Impact of blood viscosity on wake-up stroke: analysis stratified by age and stroke subtype","volume":"474","author":"Okumura","year":"2025","journal-title":"J Neurol Sci"},{"key":"B28","doi-asserted-by":"publisher","first-page":"1616847","DOI":"10.3389\/fneur.2025.1616847","article-title":"Correlation between the hemoglobin-to-hematocrit ratio and 3-month outcomes in patients with acute ischemic stroke: a secondary analysis based on a prospective cohort study","volume":"16","author":"Liu","year":"2025","journal-title":"Front Neurol"},{"key":"B29","doi-asserted-by":"publisher","first-page":"2998","DOI":"10.1093\/eurheartj\/ehad338","article-title":"Stroke in patients with heart failure and reduced or preserved ejection fraction","volume":"44","author":"Yang","year":"2023","journal-title":"Eur Heart J"},{"key":"B30","doi-asserted-by":"publisher","first-page":"102389","DOI":"10.1016\/j.jchf.2024.12.008","article-title":"Stroke in heart failure with reduced ejection fraction: systematic review and meta-analysis of randomized trials","volume":"13","author":"Gallone","year":"2025","journal-title":"JACC Heart Fail"},{"key":"B31","doi-asserted-by":"publisher","first-page":"2066","DOI":"10.1002\/ehf2.15216","article-title":"Heart failure, dementia is associated with increased stroke severity, in-hospital mortality and complications","volume":"12","author":"Zuo","year":"2025","journal-title":"ESC Heart Fail"},{"key":"B32","doi-asserted-by":"publisher","first-page":"388","DOI":"10.1097\/MEJ.0000000000001171","article-title":"High-flow nasal cannula oxygen therapy versus noninvasive ventilation in acute respiratory failure related to suspected or confirmed acute heart failure: a systematic review with meta-analysis","volume":"31","author":"Marjanovic","year":"2024","journal-title":"Eur J Emerg Med"},{"key":"B33","doi-asserted-by":"publisher","first-page":"108470","DOI":"10.1016\/j.clineuro.2024.108470","article-title":"Acute kidney injury is associated with soluble vascular cell adhesion molecule 1 levels and short-term mortality in patients with ischemic stroke","volume":"245","author":"Jaqueto","year":"2024","journal-title":"Clin Neurol Neurosurg"},{"key":"B34","doi-asserted-by":"publisher","first-page":"e214655","DOI":"10.1212\/WNL.0000000000214655","article-title":"Contrast-Associated acute kidney injury after thrombectomy for ischemic stroke: prognostic impact and CAN-REST predictive score","volume":"106","author":"Schwarz","year":"2026","journal-title":"Neurology"},{"key":"B35","doi-asserted-by":"publisher","first-page":"106001","DOI":"10.1016\/j.ebiom.2025.106001","article-title":"Beyond mild, moderate, and severe traumatic brain injury: modelling severity from clinical, neuroimaging, and blood-based indicators","volume":"121","author":"Nelson","year":"2025","journal-title":"EBioMedicine"},{"key":"B36","doi-asserted-by":"publisher","first-page":"705","DOI":"10.1007\/s13311-023-01377-1","article-title":"Hemorrhagic conversion of acute ischemic stroke","volume":"20","author":"Zubair","year":"2023","journal-title":"Neurotherapeutics"},{"key":"B37","doi-asserted-by":"publisher","first-page":"e71654","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","year":"2025","journal-title":"J Med Internet Res"},{"key":"B38","doi-asserted-by":"publisher","first-page":"101996","DOI":"10.1016\/j.smrv.2024.101996","article-title":"Obstructive sleep apnea and obesity: a review of epidemiology, pathophysiology and the effect of weight-loss treatments","volume":"78","author":"Messineo","year":"2024","journal-title":"Sleep Med Rev"},{"key":"B39","doi-asserted-by":"publisher","first-page":"e71146","DOI":"10.1002\/brb3.71146","article-title":"Prediction for respiratory failure in ischemic stroke patients admitted to ICU: a retrospective analysis based on MIMIC-IV database","volume":"15","author":"Liu","year":"2025","journal-title":"Brain Behav"},{"key":"B40","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1007\/s10143-024-03143-z","article-title":"Prevalence and risk factors of sarcopenia in patients with stroke: a systematic review and meta-analysis","volume":"48","author":"He","year":"2024","journal-title":"Neurosurg Rev"},{"key":"B41","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1186\/s12933-023-01983-5","article-title":"Changes in the triglyceride glucose-body mass index estimate the risk of stroke in middle-aged and older Chinese adults: a nationwide prospective cohort study","volume":"22","author":"Huo","year":"2023","journal-title":"Cardiovasc Diabetol"},{"key":"B42","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1186\/s40001-025-02309-9","article-title":"Stress hyperglycemia ratio as an important predictive indicator for severe disturbance of consciousness and all-cause mortality in critically ill patients with cerebral infarction: a retrospective study using the MIMIC-IV database","volume":"30","author":"Li","year":"2025","journal-title":"Eur J Med Res"},{"key":"B43","doi-asserted-by":"publisher","first-page":"1615051","DOI":"10.3389\/fendo.2025.1615051","article-title":"Association between glycemic variability and acute kidney injury incidence in patients with cerebral infarction: an analysis of the MIMIC-IV database","volume":"16","author":"Hua","year":"2025","journal-title":"Front Endocrinol (Lausanne)"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1945368\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T10:14:40Z","timestamp":1788948880000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1945368\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,9]]},"references-count":43,"alternative-id":["10.3389\/fmed.2026.1945368"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1945368","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,9]]},"article-number":"1945368"}}