{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T05:07:57Z","timestamp":1784092077776,"version":"3.55.0"},"reference-count":38,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T00:00:00Z","timestamp":1784073600000},"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. Immunol."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This retrospective cohort study enrolled 20,538 middle-aged and older patients with acute ischemic stroke (AIS) to identify immune-metabolic clinical subtypes by unsupervised clustering, to examine the differential association between subtype characteristics and post-stroke epilepsy (PSE) susceptibility, and to clarify immune-related threshold biomarkers for individualized PSE risk stratification.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Seven standardized variables were used for K-means clustering: age; National Institutes of Health Stroke Scale (NIHSS) score; lipid profile components (triglycerides, low-density lipoprotein cholesterol [LDL-c], high-density lipoprotein cholesterol [HDL-c]); glycated hemoglobin (HbA1c); and the immune-inflammatory marker C-reactive protein (CRP). Two immune-metabolic subtypes were determined. Multivariable logistic regression was performed to quantify the association between Cluster and PSE. An Extra Trees\u2013based SHapley Additive exPlanations (SHAP) framework was used to interpret the hierarchical contribution of immune and metabolic indicators to PSE risk within each subtype.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Clustering produced two clinically distinct subtypes. Cluster 1, the inflammatory-neurological deficit cluster (n = 7,790), had older age, higher NIHSS scores, higher CRP, and higher HDL-c. Cluster 2, the metabolic dysregulation cluster (n = 12,748), had higher HbA1c, LDL-c, and triglycerides (TG). The incidence of PSE was substantially higher in the inflammatory-neurological deficit cluster than in the metabolic dysregulation cluster (7.2% vs. 2.4%,\n                      <jats:italic>P<\/jats:italic>\n                      \u00a0&amp;lt;\u00a00.001). After full adjustment, membership in the inflammatory-neurological deficit cluster was associated with 4.31-fold higher odds of PSE. Extra Trees\u2013based SHAP analysis identified distinct drivers in each cluster. In the inflammatory-neurological deficit cluster, CRP emerged as the leading predictor with a risk-acceleration threshold above 24 mg\/L. In the metabolic dysregulation cluster, NIHSS was the top predictor, and HbA1c values below 7% were associated with a protective effect.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Unsupervised clustering separated AIS patients into two subtypes. The inflammatory-neurological deficit cluster had higher PSE risk. Cluster-specific SHAP results suggested candidate thresholds for individualized risk assessment.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fimmu.2026.1879446","type":"journal-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T04:42:49Z","timestamp":1784090569000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Inflammatory-neurological deficit versus metabolic dysregulation: unsupervised clustering and SHAP analysis"],"prefix":"10.3389","volume":"17","author":[{"given":"Ziying","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Postgraduate, School of Clinical Medicine, Beihua University","place":["Jilin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingling","family":"Wang","sequence":"additional","affiliation":[{"name":"Stroke Unit, Affiliated Hospital of Beihua University","place":["Jilin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,15]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejro.2023.100527","article-title":"Epidemiology, organization, diagnosis and treatment of acute ischemic stroke","volume":"11","author":"Capirossi","year":"2023","journal-title":"Eur J Radiol Open"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/7692215","article-title":"Poststroke seizure and epilepsy: A review of incidence, risk factors, diagnosis, pathophysiology, and pharmacological therapies","volume":"2022","author":"Phan","year":"2022","journal-title":"Oxid Med Cell Longev"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuint.2019.01.025","article-title":"Local and systemic metabolic alterations in brain, plasma, and liver of rats in response to aging and ischemic stroke, as detected by nuclear magnetic resonance (NMR) spectroscopy","volume":"127","author":"Wesley","year":"2019","journal-title":"Neurochem Int"},{"key":"B4","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1007\/s11306-026-02439-z","article-title":"Time-dependent plasma metabolic shifts and mechanistic insights into systemic consequences of cerebral ischemia in middle-aged patients","volume":"22","author":"Baranovicova","year":"2026","journal-title":"Metabolomics"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.3390\/antiox13060634","article-title":"Ischemic brain injury: Involvement of lipids in the pathophysiology of stroke and therapeutic strategies","volume":"13","author":"Bernoud-Hubac","year":"2024","journal-title":"Antioxidants (Basel)"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.3389\/fnagi.2021.821336","article-title":"Elevated glycated hemoglobin levels are associated with poor outcome in acute ischemic stroke","volume":"13","author":"Dong","year":"2022","journal-title":"Front Aging Neurosci"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.3389\/fneur.2019.00974","article-title":"Elevated blood C-reactive protein levels in patients with epilepsy: A systematic review and meta-analysis","volume":"10","author":"Zhong","year":"2019","journal-title":"Front Neurol"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1007\/s40266-021-00837-7","article-title":"Seizures and epilepsy after stroke: Epidemiology, biomarkers and management","volume":"38","author":"Galovic","year":"2021","journal-title":"Drugs Aging"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1161\/HYPERTENSIONAHA.119.14213","article-title":"Machine learning clustering for blood pressure variability applied to systolic blood pressure intervention trial (SPRINT) and the Hong Kong Community Cohort","volume":"76","author":"Tsoi","year":"2020","journal-title":"Hypertension"},{"key":"B10","doi-asserted-by":"publisher","first-page":"292","DOI":"10.1007\/s12028-023-01712-6","article-title":"Derivation of coagulation phenotypes and the association with prognosis in traumatic brain injury: A cluster analysis of nationwide multicenter study","volume":"40","author":"Fujiwara","year":"2024","journal-title":"Neurocrit Care"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1016\/j.eclinm.2025.103186","article-title":"MRI-based habitat radiomics combined with vision transformer for identifying vulnerable intracranial atherosclerotic plaques and predicting stroke events: A multicenter, retrospective study","volume":"82","author":"Gao","year":"2025","journal-title":"EClinicalMedicine"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1016\/j.diabres.2026.113311","article-title":"Data-driven subtypes of type 2 diabetes and risk of dementia, stroke, and brain structural changes in the UK Biobank","volume":"237","author":"Han","year":"2026","journal-title":"Diabetes Res Clin Pract"},{"key":"B13","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1186\/s12933-026-03080-9","article-title":"The joint association of the combined triglyceride-glucose index and atherogenic index of plasma with hypertension on stroke risk across different glycemic status: A prospective cohort study","volume":"25","author":"Zou","year":"2026","journal-title":"Cardiovasc Diabetol"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2024.1450317","article-title":"Advancing non-alcoholic fatty liver disease prediction: A comprehensive machine learning approach integrating SHAP interpretability and multi-cohort validation","volume":"15","author":"Yang","year":"2024","journal-title":"Front Endocrinol"},{"key":"B15","doi-asserted-by":"publisher","first-page":"16865","DOI":"10.1038\/s41598-023-44155-x","article-title":"The importance of interpreting machine learning models for blood glucose prediction in diabetes: An analysis using SHAP","volume":"13","author":"Prendin","year":"2023","journal-title":"Sci Rep"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.98759","article-title":"Predictive models for secondary epilepsy in patients with acute ischemic stroke within one year","volume":"13","author":"Liu","year":"2024","journal-title":"Elife"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.5853\/jos.2019.02978","article-title":"Beyond the brain: The systemic pathophysiological response to acute ischemic stroke","volume":"22","author":"Balch","year":"2020","journal-title":"J Stroke"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2023-073738","article-title":"Associations of meat, fish and seafood consumption with kidney function in middle-aged to older Chinese: A cross-sectional study based on the Guangzhou Biobank Cohort Study","volume":"13","author":"Lu","year":"2023","journal-title":"BMJ Open"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1111\/j.1528-1167.2009.02285.x","article-title":"Recommendation for a definition of acute symptomatic seizure","volume":"51","author":"Beghi","year":"2010","journal-title":"Epilepsia"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1016\/j.seizure.2025.10.016","article-title":"Predictive factors for early post-stroke seizures in a Hispanic population","volume":"133","author":"Rodr\u00edguez","year":"2025","journal-title":"Seizure"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.2147\/NDT.S473483","article-title":"Risk factors for post-stroke seizures in a tertiary care center: A case-control study","volume":"20","author":"Mohamed","year":"2024","journal-title":"Neuropsychiatr Dis Treat"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1016\/j.jns.2020.117138","article-title":"Prevalence and predictors of post-stroke epilepsy among Ghanaian stroke survivors","volume":"418","author":"Sarfo","year":"2020","journal-title":"J Neurol Sci"},{"key":"B23","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1186\/s12883-016-0729-6","article-title":"Clinical predictors of seizure recurrence after the first post-ischemic stroke seizure","volume":"16","author":"Kim","year":"2016","journal-title":"BMC Neurol"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1016\/j.yebeh.2025.110574","article-title":"Identifying clinical and imaging predictors of post stroke epilepsy","volume":"173","author":"Pozo Putalivo","year":"2025","journal-title":"Epilepsy Behav"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1016\/j.jstrokecerebrovasdis.2018.05.044","article-title":"The association between atrial fibrillation and poststroke seizures is influenced by ethnicity and environmental factors","volume":"27","author":"Naylor","year":"2018","journal-title":"J Stroke Cerebrovasc Dis"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.2147\/JMDH.S530478","article-title":"Correlation between liver function and risk of post-stroke epilepsy","volume":"18","author":"Zhang","year":"2025","journal-title":"J Multidiscip Healthc"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1016\/j.eplepsyres.2026.107752","article-title":"Clinical and hematologic predictors of early intensive care unit admission in seizure patients presenting to the emergency room","volume":"221","author":"Park","year":"2026","journal-title":"Epilepsy Res"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1002\/epi4.12249","article-title":"Post-stroke seizure-do the locations, types and managements of stroke matter","volume":"3","author":"Pande","year":"2018","journal-title":"Epilepsia Open"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics14232634","article-title":"The impact of the SMOTE method on machine learning and ensemble learning performance results in addressing class imbalance in data used for predicting total testosterone deficiency in type 2 diabetes patients","volume":"14","author":"Kivrak","year":"2024","journal-title":"Diagnostics (Basel)"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.3389\/fnagi.2021.781174","article-title":"Inflammation mediated epileptogenesis as possible mechanism underlying ischemic post-stroke epilepsy","volume":"13","author":"Tr\u00f6scher","year":"2021","journal-title":"Front Aging Neurosci"},{"key":"B31","doi-asserted-by":"publisher","first-page":"3779","DOI":"10.1038\/s41598-020-60628-9","article-title":"National Institutes of Health Stroke Scale (NIHSS) on admission predicts acute symptomatic seizure risk in ischemic stroke: A population-based study involving 135,117 cases","volume":"10","author":"Z\u00f6llner","year":"2020","journal-title":"Sci Rep"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1016\/j.npep.2024.102475","article-title":"Lipid metabolism: Novel approaches for managing idiopathic epilepsy","volume":"108","author":"Wang","year":"2024","journal-title":"Neuropeptides"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1016\/j.clineuro.2025.108846","article-title":"Incidence and influencing factors of post-stroke seizure after endovascular treatment of ischemic stroke - A systematic review and meta-analysis","volume":"252","author":"Isah","year":"2025","journal-title":"Clin Neurol Neurosurg"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.92134","article-title":"Risk factors associated with post-stroke epilepsy: A narrative review","volume":"17","author":"Somannagari","year":"2025","journal-title":"Cureus"},{"key":"B35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.yfrne.2014.05.003","article-title":"Estrogen-IGF-1 interactions in neuroprotection: Ischemic stroke as a case study","volume":"36","author":"Sohrabji","year":"2015","journal-title":"Front Neuroendocrinol"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1161\/STROKEAHA.111.000220","article-title":"Incidence and associations of poststroke epilepsy: The prospective South London Stroke Register","volume":"44","author":"Graham","year":"2013","journal-title":"Stroke"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-4422(17)30404-0","article-title":"Prediction of late seizures after ischaemic stroke with a novel prognostic model (the SeLECT): A multivariable prediction model development and validation study","volume":"17","author":"Galovic","year":"2018","journal-title":"Lancet Neurol"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1177\/2396987316669000","article-title":"Association between poststroke epilepsy and death: A nationwide cohort study","volume":"1","author":"Zelano","year":"2016","journal-title":"Eur Stroke J"}],"container-title":["Frontiers in Immunology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fimmu.2026.1879446\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T04:42:58Z","timestamp":1784090578000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fimmu.2026.1879446\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,15]]},"references-count":38,"alternative-id":["10.3389\/fimmu.2026.1879446"],"URL":"https:\/\/doi.org\/10.3389\/fimmu.2026.1879446","relation":{},"ISSN":["1664-3224"],"issn-type":[{"value":"1664-3224","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,15]]},"article-number":"1879446"}}