{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T15:59:27Z","timestamp":1792511967454,"version":"4.5.0"},"reference-count":21,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T00:00:00Z","timestamp":1768176000000},"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>Symptomatic intracranial hemorrhage (sICH) is a serious complication after endovascular thrombectomy (EVT) and is strongly associated with poor outcomes in acute ischemic stroke. Existing risk scores show limited predictive accuracy. This study aims to develop and externally validate a transformer-based model for predicting sICH following successful recanalization in anterior circulation large vessel occlusion.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A total of 661 EVT-treated patients were retrospectively analyzed as the derivation cohort, and 261 patients from another tertiary center were included as the external test cohort. A tabular prior-data-fitted network (TabPFN), a transformer-based foundation model, was constructed using angiographic biomarkers (basal ganglia blush, early venous filling), baseline ASPECT score, fasting blood glucose, collateral status, and the number of retriever passes. Logistic regression and XGBoost were also developed. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), precision, recall, and F1 score, and subsequently compared with established scores (ASIAN, TAG, IER-sICH).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      In internal validation, TabPFN achieved an AUC of 0.948, comparable to XGBoost (0.953) and logistic regression (0.944), but superior to ASIAN (0.786), IER-sICH (0.687), and TAG (0.670). In external validation, TabPFN demonstrated the highest AUC (0.955), significantly outperforming existing scores (all\n                      <jats:italic>p<\/jats:italic>\n                      \u202f&amp;lt;\u202f0.05), and exhibited the best F1 score and precision across cohorts.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The TabPFN model effectively predicts the risk of sICH in Chinese stroke cohorts, enabling real-time risk stratification for antithrombotic therapy and postoperative blood pressure management.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fneur.2025.1698741","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T09:46:33Z","timestamp":1768211193000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Utilizing prior-data-fitted networks and in-context learning: a transformer-based tabular foundation model for predicting symptomatic intracranial hemorrhage after successful recanalization"],"prefix":"10.3389","volume":"16","author":[{"given":"Zheng","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiayue","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengbing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Penglun","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fenglin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohua","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongxin","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,1,12]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1016\/S1474-4422(20)30102-2","article-title":"Prehospital stroke management in the thrombectomy era","volume":"19","author":"Fassbender","year":"2020","journal-title":"Lancet Neurol"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"e344","DOI":"10.1161\/STR.0000000000000215","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: a guideline for healthcare professionals from the American Heart Association\/American Stroke Association","volume":"50","author":"Powers","year":"2019","journal-title":"Stroke"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"2818","DOI":"10.1161\/STROKEAHA.121.036195","article-title":"Determinants of symptomatic intracranial hemorrhage after endovascular stroke treatment: a retrospective cohort study","volume":"53","author":"Van Der Steen","year":"2022","journal-title":"Stroke"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"1867","DOI":"10.1007\/s00415-020-10364-x","article-title":"Pre-procedural predictive factors of symptomatic intracranial hemorrhage after thrombectomy in stroke","volume":"268","author":"Venditti","year":"2021","journal-title":"J Neurol"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"2690","DOI":"10.1161\/STROKEAHA.120.030173","article-title":"Symptomatic intracranial hemorrhage after mechanical Thrombectomy in Chinese ischemic stroke patients the ASIAN score","volume":"51","author":"Zhang","year":"2020","journal-title":"Stroke"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"1370","DOI":"10.1136\/jnnp-2019-321184","article-title":"Predicting symptomatic intracranial haemorrhage after mechanical thrombectomy: the TAG score","volume":"90","author":"Montalvo","year":"2019","journal-title":"J Neurol Neurosurg Psychiatry"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"909","DOI":"10.1161\/STROKEAHA.118.023316","article-title":"IER-SICH nomogram to predict symptomatic intracerebral hemorrhage after Thrombectomy for stroke","volume":"50","author":"Cappellari","year":"2019","journal-title":"Stroke"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"476","DOI":"10.1161\/STROKEAHA.122.040065","article-title":"Symptomatic intracranial hemorrhage after endovascular stroke treatment: external validation of prediction models","volume":"54","author":"Van Der Ende","year":"2023","journal-title":"Stroke"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"3570","DOI":"10.1016\/j.jstrokecerebrovasdis.2018.08.026","article-title":"Improving the accuracy of scores to predict gastrostomy after intracerebral hemorrhage with machine learning","volume":"27","author":"Garg","year":"2018","journal-title":"J Stroke Cerebrovasc Dis"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1136\/jnis-2023-020336","article-title":"Early venous filling after mechanical thrombectomy in acute ischemic stroke due to large vessel occlusion in anterior circulation","volume":"16","author":"Li","year":"2024","journal-title":"J NeuroInterv Surg"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1016\/j.neurad.2022.07.001","article-title":"Value of angiographic regional circulation signs in predicting hemorrhagic transformation after endovascular thrombectomy","volume":"50","author":"Yu","year":"2023","journal-title":"J Neuroradiol"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"3840","DOI":"10.1007\/s00330-023-10432-6","article-title":"Prediction of cerebral hemorrhagic transformation after thrombectomy using a deep learning of dual-energy CT","volume":"34","author":"Heo","year":"2023","journal-title":"Eur Radiol"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1016\/j.jclinepi.2020.12.005","article-title":"Penalization and shrinkage methods produced unreliable clinical prediction models especially when sample size was small","volume":"132","author":"Riley","year":"2021","journal-title":"J Clin Epidemiol"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1038\/s41586-024-08328-6","article-title":"Accurate predictions on small data with a tabular foundation model","volume":"637","author":"Hollmann","year":"2025","journal-title":"Nature"},{"key":"ref15","article-title":"A transformer that solves small tabular classification problems in a second","author":"Hollmann","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1136\/neurintsurg-2018-014185","article-title":"Inter- and intraobserver reliability for angiographic leptomeningeal collateral flow assessment by the American Society of Interventional and Therapeutic Neuroradiology\/Society of Interventional Radiology (ASITN\/SIR) scale","volume":"11","author":"Ben Hassen","year":"2019","journal-title":"J NeuroInterv Surg"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"1181","DOI":"10.1001\/jamaneurol.2014.1210","article-title":"Symptomatic intracerebral hemorrhage in acute ischemic stroke after thrombolysis with intravenous recombinant tissue plasminogen activator","volume":"71","author":"Yaghi","year":"2014","journal-title":"JAMA Neurol"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1159\/000527193","article-title":"Predictors of symptomatic intracranial hemorrhage after endovascular Thrombectomy in acute ischemic stroke: a systematic review and Meta-analysis","volume":"52","author":"Dong","year":"2023","journal-title":"Cerebrovasc Dis"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"774","DOI":"10.1016\/s0895-4356(01)00341-9","article-title":"Internal validation of predictive models: efficiency of some procedures for logistic regression analysis","volume":"54","author":"Steyerberg","year":"2001","journal-title":"J Clin Epidemiol"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"S574","DOI":"10.21037\/jtd.2019.01.25","article-title":"Developing prediction models for clinical use using logistic regression: an overview","volume":"11","author":"Shipe","year":"2019","journal-title":"J Thorac Dis"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2505.16226","article-title":"Realistic evaluation of TabPFN v2 in open environments","author":"Cheng","year":"2025","journal-title":"arXiv"}],"container-title":["Frontiers in Neurology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2025.1698741\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T09:46:34Z","timestamp":1768211194000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2025.1698741\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,12]]},"references-count":21,"alternative-id":["10.3389\/fneur.2025.1698741"],"URL":"https:\/\/doi.org\/10.3389\/fneur.2025.1698741","relation":{},"ISSN":["1664-2295"],"issn-type":[{"value":"1664-2295","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,12]]},"article-number":"1698741"}}