{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T05:20:28Z","timestamp":1787721628528,"version":"build-2784847793"},"reference-count":22,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T00:00:00Z","timestamp":1787702400000},"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. Neurol."],"abstract":"<jats:sec>\n                    <jats:title>Background and purpose<\/jats:title>\n                    <jats:p>Accurate early prediction of long-term functional outcomes in acute ischemic stroke (AIS) remains challenging. We aimed to develop and validate an interpretable machine learning model integrating baseline multimodal CT perfusion and clinical data to predict 9-month poor functional outcome [modified Rankin Scale (mRS) 3\u20136] in AIS patients undergoing endovascular or surgical intervention.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective study included 371 AIS patients who underwent endovascular or surgical intervention. We integrated clinical variables, laboratory markers, CT perfusion parameters (Tmax, cerebral blood flow, and cerebral blood volume), and quantitative CT density measurements [Hounsfield units on the affected and healthy sides, normalized water uptake (NWU), Alberta Stroke Program Early CT Score (ASPECT score)]. Feature selection was performed using LASSO regression followed by SHAP-based refinement. Four algorithms\u2014Logistic Regression, Random Forest, Support Vector Machine, and XGBoost\u2014were compared. Model performance was evaluated using area under the receiver operating characteristic curve (AUC), sensitivity, specificity, F1-score, Brier score, calibration curves, and decision curve analysis (DCA). SHAP analysis was used to enhance model interpretability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Eleven predictors were selected by LASSO; after SHAP-based refinement, ten remained in the final model. The XGBoost model achieved the best performance, with an AUC of 0.956 (95% CI 0.917\u20130.995), sensitivity of 0.932, specificity of 0.897, F1-score of 0.938, and Brier score of 0.0713 (95% CI 0.0438\u20130.1135). SHAP analysis identified door-to-intervention interval (DTI) (mean SHAP\u202f=\u202f0.95) as the most influential predictor, followed by HU_affected (0.88), CBV\u202f&amp;lt;\u202f42% (0.82), NLR (0.78), blood glucose (0.74), age (0.70), gender (0.68), ASPECT score (0.66), HU_healthy (0.50), and NWU (0.48). Calibration curves demonstrated excellent agreement between predicted and observed outcomes, and DCA confirmed superior net benefit of the XGBoost model across clinically relevant thresholds (0.01\u20130.60).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>We developed an interpretable XGBoost-based model integrating baseline multimodal CT perfusion and clinical data that accurately predicts 9-month functional outcomes in AIS patients undergoing endovascular or surgical intervention. DTI, HU_affected, and CBV\u202f&amp;lt;\u202f42% emerged as the dominant predictors, highlighting the prognostic importance of time-to-reperfusion and baseline tissue injury. After external validation, this model may serve as a practical tool for early risk stratification and individualized rehabilitation planning.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fneur.2026.1877613","type":"journal-article","created":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T04:42:51Z","timestamp":1787719371000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Development and validation of an interpretable machine learning model integrating baseline multimodal CT perfusion and clinical data for predicting 9-month functional outcomes in acute ischemic stroke"],"prefix":"10.3389","volume":"17","author":[{"given":"Guizhi","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Medical Technology, Chongqing Three Gorges Medical College","place":["Chongqing, China"]},{"name":"Research Centre of Oral Materials and Technology, Chongqing Three Gorges Medical College","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanli","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Medical Technology, Chongqing Three Gorges Medical College","place":["Chongqing, China"]},{"name":"Research Centre of Oral Materials and Technology, Chongqing Three Gorges Medical College","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Radiology, People's Hospital Affiliated to Chongqing Three Gorges Medical College","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Radiology, People's Hospital Affiliated to Chongqing Three Gorges Medical College","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Li","sequence":"additional","affiliation":[{"name":"Radiology of Neurology, Chongqing University Three Gorges Hospital","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Medical Technology, Chongqing Three Gorges Medical College","place":["Chongqing, China"]},{"name":"Research Centre of Oral Materials and Technology, Chongqing Three Gorges Medical College","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Radiology, People's Hospital Affiliated to Chongqing Three Gorges Medical College","place":["Chongqing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,26]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"795","DOI":"10.1016\/S1474-4422(21)00252-0","article-title":"Global, regional, and national burden of stroke and its risk factors, 1990-2019: a systematic analysis for the global burden of disease study 2019","volume":"20","year":"2021","journal-title":"Lancet Neurol"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"e254","DOI":"10.1161\/CIR.0000000000000950","article-title":"Heart disease and stroke statistics-2021 update: a report from the American Heart Association","volume":"143","author":"Virani","year":"2021","journal-title":"Circulation"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"878","DOI":"10.1136\/jnis-2023-020411","article-title":"Endovascular therapy in acute ischemic stroke with poor reperfusion is associated with worse outcomes compared with best medical management: a HERMES substudy","volume":"16","author":"Rex","year":"2024","journal-title":"J Neurointerv Surg"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"1161016","DOI":"10.3389\/fnagi.2023.1161016","article-title":"Development and validation of a nomogram model for predicting unfavorable functional outcomes in ischemic stroke patients after acute phase","volume":"15","author":"Yan","year":"2023","journal-title":"Front Aging Neurosci"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"9985911","DOI":"10.21203\/rs.3.rs-9985911\/v1","article-title":"Advanced multimodal AI for predicting long-term functional outcomes after ischemic stroke using only admission data","volume":"1","author":"McBride","year":"2026","journal-title":"Res Sq"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"1093392","DOI":"10.3389\/fneur.2022.1093392","article-title":"National Institutes of Health stroke scale (NIHSS) scoring inconsistencies between neurologists and emergency room nurses","volume":"13","author":"Comer","year":"2022","journal-title":"Front Neurol"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"2267","DOI":"10.3390\/biomedicines10092267","article-title":"Predicting outcome in patients with brain injury: differences between machine learning versus conventional statistics","volume":"10","author":"Cerasa","year":"2022","journal-title":"Biomedicine"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"312","DOI":"10.5853\/jos.2023.03426","article-title":"A multimodal ensemble deep learning model for functional outcome prognosis of stroke patients","volume":"26","author":"Jung","year":"2024","journal-title":"J Stroke"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"1256592","DOI":"10.3389\/fnins.2023.1256592","article-title":"The predictive performance of artificial intelligence on the outcome of stroke: a systematic review and meta-analysis","volume":"17","author":"Yang","year":"2023","journal-title":"Front Neurosci"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"842","DOI":"10.3390\/diagnostics13050842","article-title":"XGBoost-based simple three-item model accurately predicts outcomes of acute ischemic stroke","volume":"13","author":"Chung","year":"2023","journal-title":"Diagnostics (Basel)"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"1234046","DOI":"10.3389\/fneur.2023.1234046","article-title":"Interpretable machine learning for prediction of clinical outcomes in acute ischemic stroke","volume":"14","author":"Lee","year":"2023","journal-title":"Front Neurol"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"1273827","DOI":"10.3389\/fninf.2023.1273827","article-title":"Prognostic estimation for acute ischemic stroke patients undergoing mechanical thrombectomy within an extended therapeutic window using an interpretable machine learning model","volume":"17","author":"Tong","year":"2023","journal-title":"Front Neuroinform"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1111\/jon.13194","article-title":"Utilizing imaging parameters for functional outcome prediction in acute ischemic stroke: a machine learning study","volume":"34","author":"Ozkara","year":"2024","journal-title":"J Neuroimaging"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"110907","DOI":"10.1016\/j.jocn.2024.110907","article-title":"CT perfusion derived relative cerebral blood volume < 42% is negatively associated with poor functional outcomes at discharge in anterior circulation large vessel occlusion stroke","volume":"130","author":"Lakhani","year":"2024","journal-title":"J Clin Neurosci"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1097\/RLI.0000000000000430","article-title":"Computed tomography-based imaging of voxel-wise lesion water uptake in ischemic brain: relationship between density and direct Volumetry","volume":"53","author":"Broocks","year":"2018","journal-title":"Investig Radiol"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"924","DOI":"10.1002\/ana.24818","article-title":"Computed tomography-based quantification of lesion water uptake identifies patients within 4.5 hours of stroke onset: a multicenter observational study","volume":"80","author":"Minnerup","year":"2016","journal-title":"Ann Neurol"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1161\/01.STR.0000196957.55928.ab","article-title":"Time is brain--quantified","volume":"37","author":"Saver","year":"2006","journal-title":"Stroke"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"3331","DOI":"10.1161\/STROKEAHA.119.027708","article-title":"Guidelines for the early Management of Patients with Acute Ischemic Stroke: 2019 update to the 2018 guidelines for the early Management of Acute Ischemic Stroke","volume":"50","author":"Warner","year":"2019","journal-title":"Stroke"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"1723","DOI":"10.1016\/S0140-6736(16)00163-X","article-title":"Endovascular thrombectomy after large-vessel ischaemic stroke: a meta-analysis of individual patient data from five randomised trials","volume":"387","author":"Goyal","year":"2016","journal-title":"Lancet"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"2426","DOI":"10.1161\/hs1001.096194","article-title":"Stress hyperglycemia and prognosis of stroke in nondiabetic and diabetic patients: a systematic overview","volume":"32","author":"Capes","year":"2001","journal-title":"Stroke"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"1169","DOI":"10.1016\/j.jstrokecerebrovasdis.2013.01.011","article-title":"Neutrophil lymphocyte ratio as a predictor of stroke","volume":"22","author":"Tokgoz","year":"2013","journal-title":"J Stroke Cerebrovasc Dis"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1136\/bmj.310.6973.170","article-title":"Multiple significance tests: the Bonferroni method","volume":"310","author":"Bland","year":"1995","journal-title":"BMJ"}],"container-title":["Frontiers in Neurology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2026.1877613\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T04:42:54Z","timestamp":1787719374000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2026.1877613\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,26]]},"references-count":22,"alternative-id":["10.3389\/fneur.2026.1877613"],"URL":"https:\/\/doi.org\/10.3389\/fneur.2026.1877613","relation":{},"ISSN":["1664-2295"],"issn-type":[{"value":"1664-2295","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,26]]},"article-number":"1877613"}}