{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T00:11:51Z","timestamp":1790035911852,"version":"4.0.1"},"reference-count":51,"publisher":"MDPI AG","issue":"23","license":[{"start":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T00:00:00Z","timestamp":1763942400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100007632","name":"Changhua Christian Hospital","doi-asserted-by":"publisher","award":["113-CCH-IRP-085"],"award-info":[{"award-number":["113-CCH-IRP-085"]}],"id":[{"id":"10.13039\/501100007632","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background\/Objectives: Stroke is a serious neurological disorder that significantly affects patients\u2019 quality of life and overall health. The severity of a stroke can vary widely and is influenced by multiple factors, such as clinical presentation, diagnostic findings, and the site of onset. This study aimed to identify and analyze key variables that contribute to stroke severity, with a particular focus on the role of collateral circulation. Methods: This study analyzed clinical, imaging, and biochemical variables\u2014ipsilateral collateral flow on MRA, MRI unilateral\u2013bilateral stroke, systolic blood pressure (SBP), fasting plasma glucose (FPG), and blood urea nitrogen (BUN). Group differences used chi-square and Mann\u2013Whitney U tests. Class imbalance was addressed with SMOTE; Logistic Regression, Random Forest, XGBoost, and SVM were cross-validated, reporting accuracy, precision, recall, and F1 with 95% CIs. Results: Reduced or absent ipsilateral collateral flow and unilateral\u2013bilateral stroke were strongly associated with greater severity (p &lt; 0.001). SBP was significant (p = 0.034), FPG was significant (p = 0.023), and BUN was borderline (p = 0.059). SMOTE improved prediction: Random Forest achieved accuracy 83.3% (CI: 79.1\u201387.6) and F1 84.0% (CI: 79.1\u201388.9); XGBoost reached accuracy 80.2% (CI: 71.5\u201389.0) and F1 81.4% (CI: 73.8\u201389.0). Logistic Regression improved to F1 70.8% (CI: 55.4\u201386.2), whereas SVM declined to accuracy 52.2% (CI: 37.5\u201367.0). Conclusions: Collateral status and unilateral\u2013bilateral stroke are key determinants of severity; SBP and FPG add prognostic value, with BUN borderline. Tree-based ensembles trained on SMOTE-balanced data provide the most reliable predictions for risk stratification. These findings suggest that future work may focus on integrating such predictive models into Clinical Decision Support Systems (CDSSs) to enhance early risk identification, strengthen CDSSs, and enable more personalized care planning for stroke patients.<\/jats:p>","DOI":"10.3390\/diagnostics15232983","type":"journal-article","created":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T13:09:25Z","timestamp":1763989765000},"page":"2983","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Factors Influencing Stroke Severity Based on Collateral Circulation, Clinical Markers and Machine Learning"],"prefix":"10.3390","volume":"15","author":[{"given":"Jia-Lang","family":"Xu","sequence":"first","affiliation":[{"name":"Department of Applied Statistics, National Taichung University of Science and Technology, Taichung 404336, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"634","DOI":"10.2471\/BLT.16.181636","article-title":"Stroke: A global response is needed","volume":"94","author":"Johnson","year":"2016","journal-title":"Bull. World Health Organ."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"59","DOI":"10.5853\/jos.2014.16.2.59","article-title":"Stroke: Morbidity, risk factors, and care in Taiwan","volume":"16","author":"Hsieh","year":"2014","journal-title":"J. Stroke"},{"key":"ref_3","first-page":"1099","article-title":"Common carotid artery occlusion: Evaluation with duplex sonography","volume":"16","author":"Chang","year":"1995","journal-title":"Am. J. Neuroradiol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"e002012","DOI":"10.1161\/JAHA.115.002012","article-title":"Magnetic resonance angiography detection of abnormal carotid artery plaque in patients with cryptogenic stroke","volume":"4","author":"Gupta","year":"2015","journal-title":"J. Am. Heart Assoc."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1111\/j.1600-0404.1998.tb07291.x","article-title":"Stroke risk factors and development of collateral flow in carotid occlusive disease","volume":"98","author":"Hedera","year":"1998","journal-title":"Acta Neurol. Scand."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"2438","DOI":"10.1161\/STROKEAHA.115.009643","article-title":"Role of acute lesion topography in initial ischemic stroke severity and long-term functional outcomes","volume":"46","author":"Wu","year":"2015","journal-title":"Stroke"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1080\/02687038.2021.2013430","article-title":"Associations between stroke severity, aphasia severity, lesion location, and lesion size in acute stroke, and aphasia severity one year post stroke","volume":"37","author":"Helland","year":"2023","journal-title":"Aphasiology"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"533","DOI":"10.1001\/jama.2016.7653","article-title":"Logistic regression: Relating patient characteristics to outcomes","volume":"316","author":"Tolles","year":"2016","journal-title":"Jama"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"123488","DOI":"10.1016\/j.jns.2025.123488","article-title":"Risk of recurrence following acute cardioembolic stroke according to lesion size and NIHSS on admission","volume":"473","author":"Paciaroni","year":"2025","journal-title":"J. Neurol. Sci."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1016\/j.neurol.2020.03.023","article-title":"Contrast enhanced ultrasound of carotid plaque in acute ischemic stroke (CUSCAS study)","volume":"177","author":"Baud","year":"2021","journal-title":"Rev. Neurol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"114630","DOI":"10.1016\/j.expneurol.2023.114630","article-title":"The role of ferroptosis and its mechanism in ischemic stroke","volume":"372","author":"Hu","year":"2024","journal-title":"Exp. Neurol."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"3882","DOI":"10.1007\/s12035-023-03728-7","article-title":"The role of necroptosis in cerebral ischemic stroke","volume":"61","author":"Wang","year":"2024","journal-title":"Mol. Neurobiol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1238","DOI":"10.1111\/ejn.14955","article-title":"Cerebral collaterals in acute ischaemia: Implications for acute ischaemic stroke patients receiving reperfusion therapy","volume":"53","author":"Ravindran","year":"2021","journal-title":"Eur. J. Neurosci."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1177\/02841851241309523","article-title":"Assessment of collateral circulation in patients with anterior circulation stroke treated with mechanical thrombectomy as a predictor of long-term clinical outcomes","volume":"66","author":"Leus","year":"2025","journal-title":"Acta Radiol."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"587","DOI":"10.1016\/j.jval.2019.03.001","article-title":"Real-world evidence, causal inference, and machine learning","volume":"22","author":"Crown","year":"2019","journal-title":"Value Health"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"6779","DOI":"10.1111\/ejn.16585","article-title":"Evolucollateral dynamics in stroke: Evolutionary pathophysiology, remodelling and emerging therapeutic strategies","volume":"60","author":"Sinha","year":"2024","journal-title":"Eur. J. Neurosci."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Zikos, D., and DeLellis, N. (2018). CDSS-RM: A clinical decision support system reference model. BMC Med. Res. Methodol., 18.","DOI":"10.1186\/s12874-018-0587-6"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Huang, K.-Y., Hsu, Y.-L., Chung, C.-L., Chen, H.-C., Horng, M.-H., Lin, C.-H., Liu, C.-S., and Xu, J.-L. (2025). Enhancing healthcare AI stability with edge computing and machine learning for extubation prediction. Sci. Rep., 15.","DOI":"10.1038\/s41598-025-02317-z"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Huang, K.-Y., Hsu, Y.-L., Chen, H.-C., Horng, M.-H., Chung, C.-L., Lin, C.-H., Xu, J.-L., and Hou, M.-H. (2023). Developing a machine-learning model for real-time prediction of successful extubation in mechanically ventilated patients using time-series ventilator-derived parameters. Front. Med., 10.","DOI":"10.3389\/fmed.2023.1167445"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Chen, Y.-H., Luo, X.-Y., Chang, C.-H., Kuo, C.-T., Shih, S.-J., Chang, M.-Y., Weng, M.-R., Chen, I.-C., Hsu, Y.-L., and Xu, J.-L. (2025). Post-surgical fall risk prediction: A machine learning approach for spine and lower extremity procedures. Front. Med., 12.","DOI":"10.3389\/fmed.2025.1574305"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Chen, Y.H., and Xu, J.L. (2023). Applying artificial intelligence to predict falls for inpatient. Front. Med., 10.","DOI":"10.3389\/fmed.2023.1285192"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"e80351","DOI":"10.2196\/80351","article-title":"Rapid Liver Fibrosis Evaluation Using the UNet-ResNet50-32\u00d7 4d Model in Magnetic Resonance Elastography: Retrospective Study","volume":"13","author":"Su","year":"2025","journal-title":"JMIR Med. Inform."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Liu, Y., Wen, Z., Wang, Y., Zhong, Y., Wang, J., Hu, Y., Zhou, P., and Guo, S. (2024). Artificial intelligence in ischemic stroke images: Current applications and future directions. Front. Neurol., 15.","DOI":"10.3389\/fneur.2024.1418060"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1053","DOI":"10.1177\/23969873241253366","article-title":"Artificial intelligence to predict individualized outcome of acute ischemic stroke patients: The SIBILLA project","volume":"9","author":"Caliandro","year":"2024","journal-title":"Eur. Stroke J."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"108292","DOI":"10.1016\/j.jstrokecerebrovasdis.2025.108292","article-title":"Factors and outcomes associated with National Institutes of Health stroke scale scores in acute ischemic stroke patients undergoing thrombectomy in United States","volume":"34","author":"Qureshi","year":"2025","journal-title":"J. Stroke Cerebrovasc. Dis."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Chu, T., Guo, Z., Zhang, Y., Liu, Y., and Gu, Y. (2025). Study on the correlation between carotid plaque calcification types and acute ischemic stroke. Front. Neurol., 16.","DOI":"10.3389\/fneur.2025.1550014"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"e70213","DOI":"10.1002\/eng2.70213","article-title":"A Hybrid Brain Stroke Prediction Framework: Integrating Feature Selection, Classification, and Hyperparameter Optimization","volume":"7","author":"Amin","year":"2025","journal-title":"Eng. Rep."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"749","DOI":"10.4103\/jfmpc.jfmpc_1569_24","article-title":"Prevalence of stroke and associated risk factors among elderly patients in a primary care setting: A retrospective cohort study","volume":"14","author":"Alabduljabbar","year":"2025","journal-title":"J. Fam. Med. Prim. Care"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1023\/A:1022627411411","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach. Learn."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_31","unstructured":"Ho, T.K. (1995, January 14\u201316). Random decision forests. Proceedings of the 3rd International Conference on Document Analysis and Recognition, Montreal, QC, Canada."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Chen, T., and Guestrin, C. (2016, January 13\u201317). Xgboost: A scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939785"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"2137","DOI":"10.1001\/jama.2011.1650","article-title":"Level of systolic blood pressure within the normal range and risk of recurrent stroke","volume":"306","author":"Ovbiagele","year":"2011","journal-title":"Jama"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1212\/WNL.53.1.126","article-title":"Baseline NIH Stroke Scale score strongly predicts outcome after stroke: A report of the Trial of Org 10172 in Acute Stroke Treatment (TOAST)","volume":"53","author":"Adams","year":"1999","journal-title":"Neurology"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Yin, H.C., Lei, R.L., Xu, J.L., Lin, C.M., and Hsu, Y.L. (2025). Enhancing Stroke Prognosis Prediction Using Deep Convolution Neural Networks. J. Mech. Med. Biol., 25.","DOI":"10.1142\/S0219519425400391"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"821","DOI":"10.1007\/s11239-025-03135-w","article-title":"From \u201ctime is brain\u201d to \u201ctime is collaterals\u201d: Updates on the role of cerebral collateral circulation in stroke","volume":"58","author":"Marilena","year":"2025","journal-title":"J. Thromb. Thrombolysis"},{"key":"ref_37","first-page":"296","article-title":"It takes two to tango: Statistical modeling and machine learning","volume":"31","author":"Kumar","year":"2021","journal-title":"J. Glob. Sch. Mark. Sci."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1007\/s00395-008-0760-x","article-title":"Collateral circulation: Past and present","volume":"104","author":"Schaper","year":"2009","journal-title":"Basic Res. Cardiol."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1161\/01.STR.0000128697.52150.75","article-title":"Recurrent stroke in patients with symptomatic carotid artery occlusion is associated with high-volume flow to the brain and increased collateral circulation","volume":"35","author":"Rutgers","year":"2004","journal-title":"Stroke"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1224","DOI":"10.1016\/j.ejrad.2011.02.046","article-title":"Quantitative perfusion computed tomography measurements of cerebral hemodynamics: Correlation with digital subtraction angiography identified primary and secondary cerebral collaterals in internal carotid artery occlusive disease","volume":"81","author":"Cheng","year":"2012","journal-title":"Eur. J. Radiol."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"S136","DOI":"10.1016\/j.annemergmed.2018.08.350","article-title":"345 Impact of Emergency Department Blood Pressure on Stroke Severity","volume":"72","author":"Roka","year":"2018","journal-title":"Ann. Emerg. Med."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.atherosclerosis.2021.08.011","article-title":"Blood urea nitrogen, blood urea nitrogen to creatinine ratio and incident stroke: The Dongfeng-Tongji cohort","volume":"333","author":"Peng","year":"2021","journal-title":"Atherosclerosis"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1186\/1865-1380-5-3","article-title":"The impact of blood pressure hemodynamics in acute ischemic stroke: A prospective cohort study","volume":"5","author":"Stead","year":"2012","journal-title":"Int. J. Emerg. Med."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J. Artif. Intell. Res."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"888","DOI":"10.1016\/S0140-6736(87)92861-3","article-title":"Stroke risk in patients with carotid stenosis","volume":"329","author":"Autret","year":"1987","journal-title":"Lancet"},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"547","DOI":"10.1186\/s40001-024-02147-1","article-title":"Predicting stroke severity of patients using interpretable machine learning algorithms","volume":"29","author":"Azar","year":"2024","journal-title":"Eur. J. Med. Res."},{"key":"ref_47","first-page":"953","article-title":"The clinical and imaging data fusion model for single-period cerebral CTA collateral circulation assessment","volume":"32","author":"Ma","year":"2024","journal-title":"J. X-Ray Sci. Technol."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"1692","DOI":"10.3390\/biomedinformatics4030091","article-title":"Automated classification of collateral circulation for ischemic stroke in cone-beam ct images using vgg11: A deep learning approach","volume":"4","author":"Ali","year":"2024","journal-title":"BioMedInformatics"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"107584","DOI":"10.1016\/j.jstrokecerebrovasdis.2024.107584","article-title":"Automated evaluation of collateral circulation for outcome prediction in acute ischemic stroke","volume":"33","author":"Scavasine","year":"2024","journal-title":"J. Stroke Cerebrovasc. Dis."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"1247","DOI":"10.1161\/STROKEAHA.120.034019","article-title":"Posterior National Institutes of Health Stroke Scale improves prognostic accuracy in posterior circulation stroke","volume":"53","author":"Alemseged","year":"2022","journal-title":"Stroke"},{"key":"ref_51","first-page":"82","article-title":"Machine Learning for Predicting Early Functional Outcomes in Patients with Stroke. Physical and rehabilitation medicine","volume":"7","author":"Chernykh","year":"2025","journal-title":"Med. Rehabil."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/15\/23\/2983\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T13:29:03Z","timestamp":1763990943000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/15\/23\/2983"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,24]]},"references-count":51,"journal-issue":{"issue":"23","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["diagnostics15232983"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics15232983","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,24]]}}}