{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T06:09:24Z","timestamp":1789711764386,"version":"4.0.1"},"reference-count":51,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T00:00:00Z","timestamp":1789689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Key R&D Program of China","award":["2021YFC3002200"],"award-info":[{"award-number":["2021YFC3002200"]}]}],"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>Neurological injury is common after cardiac arrest (CA), but early and accurate assessment remains challenging. Existing evaluation methods often lack sensitivity and specificity. This study aims to develop and validate an interpretable machine learning model for early and reliable assessment of brain injury and its prognostic relevance in ICU patients.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this study, we analyzed 1,419 CA patients from the MIMIC-IV database, randomly split into training and validation cohorts. Six machine learning (ML) algorithms-logistic regression (LR), XGBoost, artificial neural network (ANN), random forest (RF), support vector machine (SVM), and k-nearest neighbors (KNN) were developed and evaluated. The top-performing model was interpreted using SHapley Additive exPlanations (SHAP), identifying eight key predictors of brain injury. Finally, clinical data from cardiac arrest patients at our hospital were collected for external validation to assess the model\u2019s generalizability and practical utility in an ICU setting.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among the six machine learning models, the Random Forest model achieved the highest numerical performance in both the internal test and external validation cohorts. In the internal test cohort, Random Forest achieved an ACC of 88.7%, sensitivity of 80.0%, specificity of 90.6%, F1 score of 0.714, NPV of 95.5%, PPV of 64.5%, and AUC of 0.901. In the external validation cohort, Random Forest achieved an ACC of 88.8%, sensitivity of 77.8%, specificity of 90.8%, F1 score of 0.677, NPV of 95.8%, PPV of 60.0%, and AUC of 0.889. SHAP analysis identified eight influential predictors: age, hemoglobin, OASIS, temperature, blood urea nitrogen, white blood cell count, non-invasive diastolic pressure, and non-invasive systolic pressure.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Machine learning offers strong potential for early prediction of acute brain injury in in-hospital cardiac arrest patients. Our interpretable model addresses the \u201cblack box\u201d concern by providing transparent insights into key predictive features.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fneur.2026.1887511","type":"journal-article","created":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T05:39:42Z","timestamp":1789709982000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Early prediction of in-hospital acute brain injury following cardiac arrest using machine learning: development and external validation"],"prefix":"10.3389","volume":"17","author":[{"given":"Yanxiang","family":"Niu","sequence":"first","affiliation":[{"name":"Institute of Disaster and Emergency Medicine, Tianjin University","place":["Tianjin, China"]},{"name":"Tianjin University School of Medicine, Tianjin University","place":["Tianjin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Xu","sequence":"additional","affiliation":[{"name":"Institute of Disaster and Emergency Medicine, Tianjin University","place":["Tianjin, China"]},{"name":"Tianjin University School of Medicine, Tianjin University","place":["Tianjin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianqi","family":"Fan","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University","place":["Tianjin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinxiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, Tianjin Medical University General Hospital","place":["Tianjin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziquan","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Disaster and Emergency Medicine, Tianjin University","place":["Tianjin, China"]},{"name":"Tianjin University School of Medicine, Tianjin University","place":["Tianjin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guowu","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, Tianjin Medical University General Hospital","place":["Tianjin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haojun","family":"Fan","sequence":"additional","affiliation":[{"name":"Institute of Disaster and Emergency Medicine, Tianjin University","place":["Tianjin, China"]},{"name":"Tianjin University School of Medicine, Tianjin University","place":["Tianjin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,18]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"1200","DOI":"10.1001\/jama.2019.1696","article-title":"In-hospital cardiac arrest: a review","volume":"321","author":"Andersen","year":"2019","journal-title":"JAMA"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"1269","DOI":"10.1016\/S0140-6736(21)00953-3","article-title":"Brain injury after cardiac arrest","volume":"398","author":"Perkins","year":"2021","journal-title":"Lancet (London, England)"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"1393","DOI":"10.1007\/s00134-021-06548-2","article-title":"Brain injury after cardiac arrest: pathophysiology, treatment, and prognosis","volume":"47","author":"Sandroni","year":"2021","journal-title":"Intensive Care Med"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"1972","DOI":"10.1007\/s00134-013-3043-4","article-title":"Intensive care unit mortality after cardiac arrest: the relative contribution of shock and brain injury in a large cohort","volume":"39","author":"Lemiale","year":"2013","journal-title":"Intensive Care Med"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"e517","DOI":"10.1161\/CIR.0000000000000702","article-title":"Standards for studies of neurological prognostication in comatose survivors of cardiac arrest: a scientific statement from the American Heart Association","volume":"140","author":"Geocadin","year":"2019","journal-title":"Circulation"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1007\/s12028-023-01688-3","article-title":"Guidelines for neuroprognostication in comatose adult survivors of cardiac arrest","volume":"38","author":"Rajajee","year":"2023","journal-title":"Neurocrit Care"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1016\/j.resuscitation.2021.02.012","article-title":"European resuscitation council and European Society of Intensive Care Medicine guidelines 2021: post-resuscitation care","volume":"161","author":"Nolan","year":"2021","journal-title":"Resuscitation"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"e1238","DOI":"10.1212\/WNL.0000000000013301","article-title":"Regional distribution of brain injury after cardiac arrest: clinical and electrographic correlates","volume":"98","author":"Snider","year":"2022","journal-title":"Neurology"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1016\/j.resuscitation.2021.06.020","article-title":"Multimodal monitoring including early EEG improves stratification of brain injury severity after pediatric cardiac arrest","volume":"167","author":"Topjian","year":"2021","journal-title":"Resuscitation"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"5759","DOI":"10.1038\/s41598-023-32899-5","article-title":"Explainable artificial intelligence-based prediction of poor neurological outcome from head computed tomography in the immediate post-resuscitation phase","volume":"13","author":"Kawai","year":"2023","journal-title":"Sci Rep"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"110049","DOI":"10.1016\/j.resuscitation.2023.110049","article-title":"Electroencephalogram-based machine learning models to predict neurologic outcome after cardiac arrest: a systematic review","volume":"194","author":"Chen","year":"2024","journal-title":"Resuscitation"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1186\/s12871-023-02138-5","article-title":"Prediction model of in-hospital mortality in intensive care unit patients with cardiac arrest: a retrospective analysis of the MIMIC-IV database based on machine learning","volume":"23","author":"Sun","year":"2023","journal-title":"BMC Anesthesiol"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"16325","DOI":"10.20452\/pamw.16325","article-title":"A nomogram to predict in-hospital mortality in post-cardiac arrest patients: a retrospective cohort study","volume":"133","author":"Chen","year":"2023","journal-title":"Pol Arch Intern Med"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"110359","DOI":"10.1016\/j.resuscitation.2024.110359","article-title":"Prediction of neurologic outcome after out-of-hospital cardiac arrest: an interpretable approach with machine learning","volume":"202","author":"Rawshani","year":"2024","journal-title":"Resuscitation"},{"key":"ref15","first-page":"4765","volume-title":"Advances in Neural Information Processing Systems 30","author":"Lundberg","year":"2017"},{"key":"ref16","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":"ref17","first-page":"1","author":"Gaur","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"5447","DOI":"10.1007\/s10639-023-12007-w","article-title":"An empirical assessment of SMOTE variants techniques and interpretation methods in improving the accuracy and the interpretability of student performance models","volume":"29","author":"Sahlaoui","year":"2024","journal-title":"Educ Inf Technol"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"104814","DOI":"10.1016\/j.knosys.2019.06.022","article-title":"SMOTE based class-specific extreme learning machine for imbalanced learning","volume":"187","author":"Raghuwanshi","year":"2020","journal-title":"Knowl Based Syst"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1007\/s11334-022-00509-8","article-title":"A systematic method for diagnosis of hepatitis disease using machine learning","volume":"19","author":"Sachdeva","year":"2023","journal-title":"Innov Syst Softw Eng"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1007\/978-981-19-3590-9_37","volume-title":"Effective Heart Disease Prediction Using Machine Learning-Modified knn","author":"Jaya","year":""},{"key":"ref22","doi-asserted-by":"publisher","first-page":"5188","DOI":"10.3390\/app13085188","article-title":"Decision support system for predicting mortality in cardiac patients based on machine learning","volume":"13","author":"Javeed","year":"2023","journal-title":"Appl Sci (Basel)"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"92","DOI":"10.3390\/info14020092","article-title":"Effective handling of missing values in datasets for classification using machine learning methods","volume":"14","author":"Palanivinayagam","year":"2023","journal-title":"Information (Basel)"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"4293","DOI":"10.32604\/cmc.2023.036710","article-title":"Reinforcing artificial neural networks through traditional machine learning algorithms for robust classification of cancer","volume":"75","author":"Waseem","year":"2023","journal-title":"Comput Mater Contin"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"2625","DOI":"10.2147\/JMDH.S416943","article-title":"A retrospective cohort study: predicting 90-day mortality for ICU trauma patients with a machine learning algorithm using XGBoost using MIMIC-III database","volume":"16","author":"Yang","year":"2023","journal-title":"J Multidiscip Healthc"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"101845","DOI":"10.1016\/j.compenvurbsys.2022.101845","article-title":"Extracting spatial effects from machine learning model using local interpretation method: an example of SHAP and XGBoost","volume":"96","author":"Li","year":"2022","journal-title":"Comput Environ Urban Syst"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"1089","DOI":"10.3390\/jcm10051089","article-title":"Prediction of neurologically intact survival in cardiac arrest patients without pre-hospital return of spontaneous circulation: machine learning approach","volume":"10","author":"Seo","year":"2021","journal-title":"J Clin Med"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"1092","DOI":"10.1161\/CIRCRESAHA.117.311312","article-title":"Cardiovascular event prediction by machine learning: the multi-ethnic study of atherosclerosis","volume":"121","author":"Ambale-Venkatesh","year":"2017","journal-title":"Circ Res"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1038\/s41746-018-0029-1","article-title":"Scalable and accurate deep learning with electronic health records","volume":"1","author":"Rajkomar","year":"2018","journal-title":"NPJ Dig Med"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.resuscitation.2019.04.007","article-title":"Deep-learning-based out-of-hospital cardiac arrest prognostic system to predict clinical outcomes","volume":"139","author":"Kwon","year":"2019","journal-title":"Resuscitation"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.resuscitation.2016.12.010","article-title":"The association between anemia and neurological outcome in hypoxic ischemic brain injury after cardiac arrest","volume":"112","author":"Wormsbecker","year":"2017","journal-title":"Resuscitation"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1016\/j.ajem.2011.03.031","article-title":"Relationship between the hemoglobin level at hospital arrival and post-cardiac arrest neurologic outcome","volume":"30","year":"2012","journal-title":"Am J Emerg Med"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1016\/j.resuscitation.2015.08.015","article-title":"Low hemoglobin levels are associated with lower cerebral saturations and poor outcome after cardiac arrest","volume":"96","author":"Ameloot","year":"2015","journal-title":"Resuscitation"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1016\/j.resuscitation.2019.05.033","article-title":"The association of immediate post cardiac arrest diastolic hypertension and survival following pediatric cardiac arrest","volume":"141","author":"Topjian","year":"2019","journal-title":"Resuscitation"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1016\/j.resuscitation.2019.01.002","article-title":"A comparison of non-invasive versus invasive measures of intracranial pressure in hypoxic ischaemic brain injury after cardiac arrest","volume":"137","author":"Cardim","year":"2019","journal-title":"Resuscitation"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1016\/j.resuscitation.2018.07.017","article-title":"The impact of diastolic blood pressure values on the neurological outcome of cardiac arrest patients","volume":"130","author":"Annoni","year":"2018","journal-title":"Resuscitation"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1016\/j.ncl.2005.10.002","article-title":"Brain injury from cardiac arrest in children","volume":"24","author":"Hickey","year":"2006","journal-title":"Neurol Clin"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1016\/j.resuscitation.2015.05.015","article-title":"The relationship between age and outcome in out-of-hospital cardiac arrest patients","volume":"94","author":"Andrew","year":"2015","journal-title":"Resuscitation"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1097\/01.ccm.0000435668.53188.80","article-title":"Serum biomarkers of brain injury to classify outcome after pediatric cardiac arrest*","volume":"42","author":"Fink","year":"2014","journal-title":"Crit Care Med"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1016\/S0090-3019(01)00414-1","article-title":"The blood leukocyte count and its prognostic significance in severe head injury","volume":"55","author":"Rovlias","year":"2001","journal-title":"Surg Neurol"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"199","DOI":"10.21037\/cdt.2016.02.06","article-title":"Therapeutic hypothermia impacts leukocyte kinetics after cardiac arrest","volume":"6","author":"Dufner","year":"2016","journal-title":"Cardiovasc Diagn Ther"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"1711","DOI":"10.1097\/CCM.0b013e31828a24fe","article-title":"A new severity of illness scale using a subset of acute physiology and chronic health evaluation data elements shows comparable predictive accuracy","volume":"41","author":"Johnson","year":"2013","journal-title":"Crit Care Med"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"1251944","DOI":"10.3389\/fneur.2023.1251944","article-title":"Predictive value of the Oxford acute severity of illness score in acute stroke patients with stroke-associated pneumonia","volume":"14","author":"Wang","year":"2023","journal-title":"Front Neurol"},{"key":"ref44","doi-asserted-by":"publisher","first-page":"e7083","DOI":"10.7717\/peerj.7083","article-title":"Prognosis predictive value of the Oxford acute severity of illness score for sepsis: a retrospective cohort study","volume":"7","author":"Chen","year":"2019","journal-title":"PeerJ"},{"key":"ref45","doi-asserted-by":"publisher","first-page":"S122","DOI":"10.1177\/2048872619860804","article-title":"Arterial blood pressure during targeted temperature management after out-of-hospital cardiac arrest and association with brain injury and long-term cognitive function","volume":"9","author":"Grand","year":"2020","journal-title":"Eur Heart J Acute Cardiovasc Care"},{"key":"ref46","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1016\/j.ncl.2008.03.015","article-title":"Management of brain injury after resuscitation from cardiac arrest","volume":"26","author":"Geocadin","year":"2008","journal-title":"Neurol Clin"},{"key":"ref47","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.resuscitation.2018.10.004","article-title":"The effect of different target temperatures in targeted temperature management on neurologically favorable outcome after out-of-hospital cardiac arrest: a nationwide multicenter observational study in Japan (the JAAM-OHCA registry)","volume":"133","author":"Irisawa","year":"2018","journal-title":"Resuscitation"},{"key":"ref48","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1016\/j.jss.2020.07.062","article-title":"The emergency department systolic blood pressure relationship after traumatic brain injury","volume":"257","author":"Asmar","year":"2021","journal-title":"J Surg Res"},{"key":"ref49","doi-asserted-by":"publisher","first-page":"1135","DOI":"10.1097\/TA.0b013e31824af90b","article-title":"Traditional systolic blood pressure targets underestimate hypotension-induced secondary brain injury","volume":"72","author":"Brenner","year":"2012","journal-title":"J Trauma Acute Care Surg"},{"key":"ref50","doi-asserted-by":"publisher","first-page":"612","DOI":"10.1016\/j.injury.2013.09.008","article-title":"The association between admission systolic blood pressure and mortality in significant traumatic brain injury: a multi-Centre cohort study","volume":"45","author":"Fuller","year":"2014","journal-title":"Injury"},{"key":"ref51","doi-asserted-by":"publisher","first-page":"333","DOI":"10.5137\/1019-5149.JTN.29843-20.2","article-title":"Evaluation of blood urea, creatinine, and glucose levels as biochemical indicators of the type and severity of traumatic brain injury","volume":"31","author":"Gul","year":"2021","journal-title":"Turk Neurosurg"}],"container-title":["Frontiers in Neurology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2026.1887511\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T05:39:44Z","timestamp":1789709984000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2026.1887511\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,18]]},"references-count":51,"alternative-id":["10.3389\/fneur.2026.1887511"],"URL":"https:\/\/doi.org\/10.3389\/fneur.2026.1887511","relation":{},"ISSN":["1664-2295"],"issn-type":[{"value":"1664-2295","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,18]]},"article-number":"1887511"}}