{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T19:50:45Z","timestamp":1792785045871,"version":"4.5.0"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T00:00:00Z","timestamp":1782172800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T00:00:00Z","timestamp":1789516800000},"content-version":"vor","delay-in-days":85,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"the Research Fund of Seoul St. Mary\u2019s Hospital, The Catholic University of Korea","award":["ZC25RISI0423"],"award-info":[{"award-number":["ZC25RISI0423"]}],"id":[{"id":"https:\/\/ror.org\/01fpnj063","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Neurological prognostication after out-of-hospital cardiac arrest (OHCA) remains challenging. Existing clinical scores rely on static, single-timepoint assessments and fail to capture the dynamic interplay among coagulation derangement, systemic inflammation, brain injury, and evolving neurological status. Whether integrating serial multimodal data through machine learning can meaningfully improve prediction over established approaches has not been systematically evaluated. We conducted a retrospective cohort study of 414 consecutive OHCA patients treated with targeted temperature management (TTM) at a tertiary cardiac arrest center in South Korea (2009\u20132021), where withdrawal of life-sustaining treatment is not practiced. Ninety-one features spanning five modalities\u2014coagulation, inflammation, brain injury biomarkers, neurological examination, and static clinical variables\u2014were extracted at admission, 24\u00a0h, and 48\u00a0h. We compared four machine learning algorithms against single-modality models and a clinical score approximation using five-fold stratified cross-validation. Dynamic prediction models evaluated discriminative performance evolution. SHapley Additive exPlanations (SHAP) analysis quantified feature- and modality-level contributions. Robustness was assessed through temporal validation, self-fulfilling prophecy sensitivity analyses, and exclusion of clinician-decision-dependent variables. Of 414 patients (mean age 55.6 years, 71.8% male), 131 (31.6%) achieved favorable neurological outcome (Cerebral Performance Category [CPC] 1\u20132) at six months. The full multimodal random forest model achieved an area under the receiver operating characteristic curve (AUROC) of 0.983 (95% CI 0.972\u20130.991), significantly outperforming the clinical score approximation (AUROC 0.847; \u0394AUROC\u2009+\u20090.136,\n                    <jats:italic>p<\/jats:italic>\n                    \u2009&lt;\u20090.001) and every single-modality model (all\n                    <jats:italic>p<\/jats:italic>\n                    \u2009&lt;\u20090.001). At 100% specificity, sensitivity was 0.519. Dynamic prediction improved from AUROC 0.950 at admission to 0.977 at 24\u00a0h (\n                    <jats:italic>p<\/jats:italic>\n                    \u2009&lt;\u20090.001) and 0.981 at 48\u00a0h. SHAP analysis revealed that neurological examination and brain injury biomarkers dominated overall prediction, while coagulation markers\u2014particularly initial international normalized ratio (INR)\u2014provided the strongest early discriminative signal. The model remained robust on temporal validation (AUROC 0.977), after neurological examination exclusion (0.965), and after excluding clinician-decision-dependent variables (0.979). A multimodal machine learning framework integrating serial thromboinflammation, brain injury, and neurological data substantially outperforms conventional approaches for neurological prognostication after OHCA. The dynamic prediction capability and modality-level explainability offer a pathway toward clinically actionable, time-evolving decision support in post-cardiac arrest care.\n                  <\/jats:p>","DOI":"10.1038\/s41598-026-59052-2","type":"journal-article","created":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T13:27:10Z","timestamp":1782221230000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A machine learning framework for multimodal temporal prediction of neurological outcome after out-of-hospital cardiac arrest"],"prefix":"10.1038","volume":"16","author":[{"given":"Jee Yong","family":"Lim","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han Joon","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,23]]},"reference":[{"key":"59052_CR1","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1016\/j.resuscitation.2021.02.007","volume":"161","author":"JT Grasner","year":"2021","unstructured":"Grasner, J. T. et al. European Resuscitation Council guidelines 2021: Epidemiology of cardiac arrest in Europe. Resuscitation 161, 61\u201379 (2021).","journal-title":"Resuscitation"},{"key":"59052_CR2","doi-asserted-by":"publisher","first-page":"e254","DOI":"10.1161\/CIR.0000000000000950","volume":"143","author":"SS Virani","year":"2021","unstructured":"Virani, S. S. et al. Heart disease and stroke statistics\u20142021 update. Circulation 143, e254\u2013e743 (2021).","journal-title":"Circulation"},{"key":"59052_CR3","doi-asserted-by":"publisher","first-page":"562","DOI":"10.1161\/01.CIR.0000023891.80661.AD","volume":"106","author":"C Adrie","year":"2002","unstructured":"Adrie, C. et al. Successful cardiopulmonary resuscitation after cardiac arrest as a sepsis-like syndrome. Circulation 106, 562\u2013568 (2002).","journal-title":"Circulation"},{"key":"59052_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.resuscitation.2025.110809","author":"C Sandroni","year":"2025","unstructured":"Sandroni, C. et al. European Resuscitation Council and European Society of Intensive Care Medicine guidelines 2025: Post-resuscitation care. Resuscitation https:\/\/doi.org\/10.1016\/j.resuscitation.2025.110809 (2025).","journal-title":"Resuscitation"},{"key":"59052_CR5","doi-asserted-by":"publisher","first-page":"e517","DOI":"10.1161\/CIR.0000000000000702","volume":"140","author":"RG Geocadin","year":"2019","unstructured":"Geocadin, R. G. et al. Standards for studies of neurological prognostication in comatose survivors of cardiac arrest: A scientific statement from the American Heart Association. Circulation 140, e517\u2013e542 (2019).","journal-title":"Circulation"},{"key":"59052_CR6","doi-asserted-by":"publisher","first-page":"S673","DOI":"10.1161\/CIR.0000000000001375","volume":"152","author":"KG Hirsch","year":"2025","unstructured":"Hirsch, K. G. et al. Part 11: Post-cardiac arrest care: 2025 American Heart Association Guidelines for cardiopulmonary resuscitation and emergency cardiovascular care. Circulation 152, S673\u2013S718 (2025).","journal-title":"Circulation"},{"key":"59052_CR7","doi-asserted-by":"publisher","first-page":"2840","DOI":"10.1093\/eurheartj\/ehl335","volume":"27","author":"C Adrie","year":"2006","unstructured":"Adrie, C. et al. Predicting survival with good neurological recovery at hospital admission after successful resuscitation of out-of-hospital cardiac arrest: The OHCA score. Eur. Heart J. 27, 2840\u20132845 (2006).","journal-title":"Eur. Heart J."},{"key":"59052_CR8","doi-asserted-by":"publisher","first-page":"3222","DOI":"10.1093\/eurheartj\/ehv556","volume":"37","author":"C Maupain","year":"2016","unstructured":"Maupain, C. et al. The CAHP (Cardiac Arrest Hospital Prognosis) score: A tool for risk stratification after out-of-hospital cardiac arrest. Eur. Heart J. 37, 3222\u20133228 (2016).","journal-title":"Eur. Heart J."},{"key":"59052_CR9","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1016\/j.jacc.2005.03.046","volume":"46","author":"C Adrie","year":"2005","unstructured":"Adrie, C. et al. Coagulopathy after successful cardiopulmonary resuscitation following cardiac arrest. J. Am. Coll. Cardiol. 46, 21\u201328 (2005).","journal-title":"J. Am. Coll. Cardiol."},{"key":"59052_CR10","doi-asserted-by":"publisher","first-page":"156","DOI":"10.3389\/fmed.2017.00156","volume":"4","author":"T Wada","year":"2017","unstructured":"Wada, T. Coagulofibrinolytic changes in patients with post-cardiac arrest syndrome. Front. Med. 4, 156 (2017).","journal-title":"Front. Med."},{"key":"59052_CR11","doi-asserted-by":"publisher","first-page":"1223","DOI":"10.1097\/CCM.0000000000000937","volume":"43","author":"J Bro-Jeppesen","year":"2015","unstructured":"Bro-Jeppesen, J. et al. Systemic inflammatory response and potential prognostic implications after out-of-hospital cardiac arrest. Crit. Care Med. 43, 1223\u20131232 (2015).","journal-title":"Crit. Care Med."},{"key":"59052_CR12","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1016\/j.thromres.2016.11.007","volume":"149","author":"M Levi","year":"2017","unstructured":"Levi, M. & van der Poll, T. Coagulation and sepsis. Thromb. Res. 149, 38\u201344 (2017).","journal-title":"Thromb. Res."},{"key":"59052_CR13","doi-asserted-by":"publisher","first-page":"890","DOI":"10.1016\/j.jfma.2023.01.005","volume":"122","author":"YH Huang","year":"2023","unstructured":"Huang, Y. H. et al. Prognostic value of neutrophil-lymphocyte ratio in out-of-hospital cardiac arrest patients receiving targeted temperature management. J. Formos. Med. Assoc. 122, 890\u2013898 (2023).","journal-title":"J. Formos. Med. Assoc."},{"key":"59052_CR14","doi-asserted-by":"publisher","first-page":"782","DOI":"10.1016\/j.resuscitation.2013.01.004","volume":"84","author":"M Annborn","year":"2013","unstructured":"Annborn, M. et al. Procalcitonin after cardiac arrest\u2014an indicator of severity of illness, ischemia-reperfusion injury and outcome. Resuscitation 84, 782\u2013786 (2013).","journal-title":"Resuscitation"},{"key":"59052_CR15","doi-asserted-by":"publisher","first-page":"1347","DOI":"10.1056\/NEJMra1814259","volume":"380","author":"A Rajkomar","year":"2019","unstructured":"Rajkomar, A., Dean, J. & Kohane, I. Machine learning in medicine. N Engl. J. Med. 380, 1347\u20131358 (2019).","journal-title":"N Engl. J. Med."},{"key":"59052_CR16","doi-asserted-by":"publisher","first-page":"1589","DOI":"10.1109\/JBHI.2017.2767063","volume":"22","author":"B Shickel","year":"2018","unstructured":"Shickel, B. et al. Deep EHR: A survey of recent advances in deep learning techniques for electronic health record analysis. IEEE J. Biomed. Health Inf. 22, 1589\u20131604 (2018).","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"59052_CR17","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1016\/j.resuscitation.2019.04.007","volume":"139","author":"JM Kwon","year":"2019","unstructured":"Kwon, J. M. et al. Deep-learning-based out-of-hospital cardiac arrest prognostic system to predict clinical outcomes. Resuscitation 139, 84\u201391 (2019).","journal-title":"Resuscitation"},{"key":"59052_CR18","doi-asserted-by":"crossref","first-page":"105778","DOI":"10.1016\/j.ijmedinf.2024.105778","volume":"195","author":"S Harford","year":"2025","unstructured":"Harford, S. et al. Post-cardiac arrest outcome prediction using machine learning: A systematic review and meta-analysis. Int. J. Med. Inf. 195, 105778 (2025).","journal-title":"Int. J. Med. Inf."},{"key":"59052_CR19","doi-asserted-by":"publisher","first-page":"e1379","DOI":"10.1002\/widm.1379","volume":"10","author":"G Stiglic","year":"2020","unstructured":"Stiglic, G. et al. Interpretability of machine learning-based prediction models in healthcare. WIREs Data Min. Knowl. Discov. 10, e1379 (2020).","journal-title":"WIREs Data Min. Knowl. Discov"},{"key":"59052_CR20","first-page":"4765","volume":"30","author":"SM Lundberg","year":"2017","unstructured":"Lundberg, S. M. & Lee, S. I. A unified approach to interpreting model predictions. Adv. Neural Inf. Process. Syst. 30, 4765\u20134774 (2017).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"59052_CR21","doi-asserted-by":"publisher","first-page":"55","DOI":"10.7326\/M14-0697","volume":"162","author":"GS Collins","year":"2015","unstructured":"Collins, G. S. et al. Transparent Reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): The TRIPOD statement. Ann. Intern. Med. 162, 55\u201363 (2015).","journal-title":"Ann. Intern. Med."},{"key":"59052_CR22","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1038\/nrneurol.2014.36","volume":"10","author":"DM Greer","year":"2014","unstructured":"Greer, D. M., Rosenthal, E. S. & Wu, O. Neuroprognostication of hypoxic-ischaemic coma in the therapeutic hypothermia era. Nat. Rev. Neurol. 10, 190\u2013203 (2014).","journal-title":"Nat. Rev. Neurol."},{"key":"59052_CR23","doi-asserted-by":"publisher","first-page":"2283","DOI":"10.1056\/NEJMoa2100591","volume":"384","author":"J Dankiewicz","year":"2021","unstructured":"Dankiewicz, J. et al. Hypothermia versus normothermia after out-of-hospital cardiac arrest. N. Engl. J. Med. 384, 2283\u20132294 (2021).","journal-title":"N. Engl. J. Med."},{"key":"59052_CR24","doi-asserted-by":"publisher","first-page":"S483","DOI":"10.1161\/CIR.0000000000000262","volume":"132","author":"CW Callaway","year":"2015","unstructured":"Callaway, C. W. et al. Part 8: Post-cardiac arrest care: 2015 AHA guidelines update. Circulation 132, S483\u2013S500 (2015).","journal-title":"Circulation"},{"key":"59052_CR25","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman, L. Random forests. Mach. Learn. 45, 5\u201332 (2001).","journal-title":"Mach. Learn."},{"key":"59052_CR26","doi-asserted-by":"crossref","unstructured":"Chen, T. & Guestrin, C. XGBoost: A scalable tree boosting system. In Proceeding of 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 785\u2013794 (ACM, 2016).","DOI":"10.1145\/2939672.2939785"},{"key":"59052_CR27","doi-asserted-by":"publisher","first-page":"m441","DOI":"10.1136\/bmj.m441","volume":"368","author":"RD Riley","year":"2020","unstructured":"Riley, R. D. et al. Calculating the sample size required for developing a clinical prediction model. BMJ 368, m441 (2020).","journal-title":"BMJ"},{"key":"59052_CR28","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1016\/j.resuscitation.2019.03.035","volume":"139","author":"SE Zhou","year":"2019","unstructured":"Zhou, S. E. et al. Distinct predictive values of current neuroprognostic guidelines in post-cardiac arrest patients. Resuscitation 139, 343\u2013350 (2019).","journal-title":"Resuscitation"},{"key":"59052_CR29","doi-asserted-by":"publisher","first-page":"2104","DOI":"10.1016\/j.jacc.2015.03.538","volume":"65","author":"P Stammet","year":"2015","unstructured":"Stammet, P. et al. Neuron-specific enolase as a predictor of death or poor neurological outcome after out-of-hospital cardiac arrest and targeted temperature management. J. Am. Coll. Cardiol. 65, 2104\u20132114 (2015).","journal-title":"J. Am. Coll. Cardiol."},{"key":"59052_CR30","doi-asserted-by":"publisher","first-page":"AIra2500585","DOI":"10.1056\/AIra2500585","volume":"2","author":"S Park","year":"2025","unstructured":"Park, S., Li, Y. & Megjhani, M. Physiological signals boosted by artificial intelligence save time and brain function. NEJM AI. 2, AIra2500585 (2025).","journal-title":"NEJM AI"},{"key":"59052_CR31","doi-asserted-by":"publisher","first-page":"AIoa2500749","DOI":"10.1056\/AIoa2500749","volume":"3","author":"J Willms","year":"2026","unstructured":"Willms, J. et al. Silent validation of a longitudinal model for predicting delayed cerebral ischemia in real time after subarachnoid hemorrhage. NEJM AI. 3, AIoa2500749 (2026).","journal-title":"NEJM AI"},{"key":"59052_CR32","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1038\/s43856-024-00666-w","volume":"4","author":"J Klug","year":"2024","unstructured":"Klug, J. et al. Machine learning for early dynamic prediction of functional outcome after stroke. Commun. Med. 4, 232 (2024).","journal-title":"Commun. Med."},{"key":"59052_CR33","doi-asserted-by":"publisher","first-page":"1112623","DOI":"10.3389\/fpubh.2023.1112623","volume":"11","author":"Y Tang","year":"2023","unstructured":"Tang, Y. et al. Association between prothrombin time-international normalized ratio and prognosis of post-cardiac arrest patients: A retrospective cohort study. Front. Public. Health. 11, 1112623 (2023).","journal-title":"Front. Public. Health"},{"key":"59052_CR34","doi-asserted-by":"publisher","first-page":"e0279653","DOI":"10.1371\/journal.pone.0279653","volume":"18","author":"HJ Kim","year":"2023","unstructured":"Kim, H. J. et al. Coagulation measures after cardiac arrest (CMACA). PLoS One. 18, e0279653 (2023).","journal-title":"PLoS One"},{"key":"59052_CR35","doi-asserted-by":"publisher","first-page":"110049","DOI":"10.1016\/j.resuscitation.2023.110049","volume":"194","author":"CC Chen","year":"2024","unstructured":"Chen, C. C. et al. Electroencephalogram-based machine learning models to predict neurologic outcome after cardiac arrest: A systematic review. Resuscitation 194, 110049 (2024).","journal-title":"Resuscitation"},{"key":"59052_CR36","first-page":"5998","volume":"30","author":"A Vaswani","year":"2017","unstructured":"Vaswani, A. et al. Attention is all you need. Adv. Neural Inf. Process. Syst. 30, 5998\u20136008 (2017).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"59052_CR37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v045.i03","volume":"45","author":"S van Buuren","year":"2011","unstructured":"van Buuren, S. & Groothuis-Oudshoorn, K. mice: Multivariate imputation by chained equations in R. J. Stat. Softw. 45, 1\u201367 (2011).","journal-title":"J. Stat. Softw."},{"key":"59052_CR38","doi-asserted-by":"publisher","first-page":"1803","DOI":"10.1007\/s00134-020-06198-w","volume":"46","author":"C Sandroni","year":"2020","unstructured":"Sandroni, C. et al. Prediction of poor neurological outcome in comatose survivors of cardiac arrest: A systematic review. Intensive Care Med. 46, 1803\u20131851 (2020).","journal-title":"Intensive Care Med."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-59052-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-59052-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-59052-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T11:03:02Z","timestamp":1789556582000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-59052-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,23]]},"references-count":38,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["59052"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-59052-2","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,23]]},"assertion":[{"value":"11 March 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study was conducted according to the guidelines of the Declaration of Helsinki and approved by the Institutional Review Board of the Catholic University of Korea, Seoul St. Mary\u2019s Hospital (KC23RISI0264; approved 21 April 2023). The requirement for informed consent was waived due to the retrospective observational design.","order":2,"name":"Ethics","label":"Ethics approval","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"28810"}}