{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T11:14:18Z","timestamp":1792062858892,"version":"4.4.0"},"posted":{"date-parts":[[2025,9,27]]},"group-title":"Neurology","reference-count":37,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T00:00:00Z","timestamp":1758931200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.medrxiv.org\/about\/FAQ#license"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,9,27]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:sec>\n                  <jats:title>Background and Objectives<\/jats:title>\n                  <jats:p>Post-ischemic stroke epilepsy (PISE) reduces quality of life, and early risk prediction can guide prevention strategies and anti-epileptogenesis treatment trials. Stroke severity predicts both PISE and mortality, and ignoring mortality can overestimate epilepsy risk. We sought to enhance PISE risk stratification by modeling death as a competing outcome, integrating quantitative clinical, neuroimaging, and electroencephalography (EEG) biomarkers to distinguish shared and distinct predictors of epilepsy and mortality.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>We developed a PISE prediction model using retrospective data from Yale-New Haven Hospital. The training cohort included patients from 2014\u20132020; the testing cohort from 2021\u20132022. Eligible patients were adults with acute ischemic stroke who underwent neuroimaging and EEG monitoring &lt;7 days post-stroke and had follow-up &gt;7 days.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>\n                    Of 280 patients, 53 developed PISE first, 104 died first, and the rest were censored. Quantitative PISE biomarkers included greater 72h stroke severity (HR\n                    <jats:sub>\u03943<\/jats:sub>\n                    [95%CI], 1.2 [1.1-1.4]), infarct volume (HR\n                    <jats:sub>\u039410mL<\/jats:sub>\n                    , 1.06 [1.04-1.08]), EEG epileptiform abnormality burden (HR\n                    <jats:sub>\u039410%<\/jats:sub>\n                    , 1.2 [1.1-1.3]), and EEG power asymmetries (HR\n                    <jats:sub>\u039410%<\/jats:sub>\n                    , 2.0 [1.4-2.9]). Death predictors included older age (HR\n                    <jats:sub>\u039410years<\/jats:sub>\n                    , 1.7 [1.4-2.0]), worse pre-stroke functional status (HR, 1.4 [1.2-1.7]), atrial fibrillation history (HR, 2.4 [1.6-3.7]), cardioembolism etiology (HR, 1.9 [1.2-3.0]), anterior cerebral artery involvement (HR, 2.2 [1.2-3.7]), and greater EEG global theta-band powers (HR\n                    <jats:sub>\u039410\u00b5V<\/jats:sub>\n                    , 6.2 [2.3-17]). Our model, CRIME\n                    <jats:sub>PISE<\/jats:sub>\n                    , integrating these features, allows prediction of PISE-first and death-first risk scores with AUC of 0.72 (95%CI, 0.60-0.83) and 0.79 (0.72-0.85), respectively. Compared with the benchmark SeLECT model, CRIME\n                    <jats:sub>PISE<\/jats:sub>\n                    better predicted PISE in patients with \u22654 SeLECT points (AUC, 0.72 vs 0.58) but not those with &lt;4 points (AUC, 0.33 vs 0.52). In the testing cohort, CRIME\n                    <jats:sub>PISE<\/jats:sub>\n                    identified a more selective group (n=18 vs 44 per SeLECT) with a higher PISE rate (39% vs 20%) and a lower mortality rate (22% vs 45%).\n                  <\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Discussion<\/jats:title>\n                  <jats:p>\n                    CRIME\n                    <jats:sub>PISE<\/jats:sub>\n                    enhances PISE prediction by accounting for mortality as a competing outcome and incorporating multimodal quantitative biomarkers. Because its benefits over SeLECT are most pronounced in high-risk patients, a two-stage approach\u2014SeLECT screening followed by CRIME\n                    <jats:sub>PISE<\/jats:sub>\n                    in SeLECT-positive cases\u2014may better target candidates for anti-epileptogenesis trials by prioritizing patients likely to survive long-term and develop epilepsy.\n                  <\/jats:p>\n                <\/jats:sec>","DOI":"10.1101\/2025.09.22.25335736","type":"posted-content","created":{"date-parts":[[2025,9,28]],"date-time":"2025-09-28T07:15:10Z","timestamp":1759043710000},"source":"Crossref","is-referenced-by-count":1,"title":["Dual-outcome Prediction of Post-Ischemic Stroke Epilepsy and Mortality Using Multimodal Quantitative Biomarkers"],"prefix":"10.64898","author":[{"given":"Yilun","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexandria L.","family":"Soto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tejaswi D.","family":"Sudhakar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adeel","family":"Zubair","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoqi","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Jing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wendong","family":"Ge","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lucas","family":"Loman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adithya","family":"Sivaraju","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9711-3340","authenticated-orcid":false,"given":"Nils","family":"Petersen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6333-832X","authenticated-orcid":false,"given":"Lawrence J.","family":"Hirsch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hal","family":"Blumenfeld","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sahar F.","family":"Zafar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aaron F.","family":"Struck","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kevin N.","family":"Sheth","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emily J.","family":"Gilmore","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"M. Brandon","family":"Westover","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3072-6198","authenticated-orcid":false,"given":"Jennifer A.","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2025093006001136000_2025.09.22.25335736v1.1","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-4422(21)00252-0"},{"key":"2025093006001136000_2025.09.22.25335736v1.2","doi-asserted-by":"crossref","first-page":"1309","DOI":"10.1111\/epi.13062","article-title":"In-hospital costs in patients with seizures and epilepsy after stroke","volume":"56","year":"2015","journal-title":"Epilepsia"},{"key":"2025093006001136000_2025.09.22.25335736v1.3","doi-asserted-by":"crossref","first-page":"605","DOI":"10.1001\/jamaneurol.2023.0611","article-title":"Association of mortality and risk of epilepsy with type of acute symptomatic seizure after ischemic stroke and an updated prognostic model","volume":"80","year":"2023","journal-title":"JAMA Neurol"},{"key":"2025093006001136000_2025.09.22.25335736v1.4","doi-asserted-by":"publisher","DOI":"10.1161\/01.STR.0000130989.17100.96"},{"key":"2025093006001136000_2025.09.22.25335736v1.5","doi-asserted-by":"publisher","DOI":"10.1007\/s40266-021-00837-7"},{"key":"2025093006001136000_2025.09.22.25335736v1.6","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1097\/WCO.0000000000000067","article-title":"Antiepileptogenesis in humans: Disappointing clinical evidence and ways to move forward","volume":"27","year":"2014","journal-title":"Curr Opin Neurol"},{"key":"2025093006001136000_2025.09.22.25335736v1.7","doi-asserted-by":"publisher","DOI":"10.1016\/S1474-4422(17)30404-0"},{"key":"2025093006001136000_2025.09.22.25335736v1.8","doi-asserted-by":"crossref","first-page":"302","DOI":"10.1684\/epd.2021.1391","article-title":"Post-stroke seizure risk prediction models: a systematic review and meta-analysis","volume":"24","year":"2022","journal-title":"Epileptic Disorders"},{"key":"2025093006001136000_2025.09.22.25335736v1.9","first-page":"108080","article-title":"Risk models to predict late-onset seizures after stroke: a systematic review","volume":"121","year":"2021","journal-title":"Epilepsy Behav"},{"key":"2025093006001136000_2025.09.22.25335736v1.10","doi-asserted-by":"publisher","DOI":"10.2147\/ndt.s324271"},{"key":"2025093006001136000_2025.09.22.25335736v1.11","doi-asserted-by":"crossref","first-page":"1273270","DOI":"10.3389\/fneur.2023.1273270","article-title":"Post-stroke seizures, epilepsy, and mortality in a prospective hospital-based study","volume":"14","year":"2023","journal-title":"Front Neurol"},{"key":"2025093006001136000_2025.09.22.25335736v1.12","first-page":"702871","article-title":"Analysis of risk factors for first seizure after stroke in chinese patients","volume":"2013","year":"2013","journal-title":"Biomed Res Int"},{"key":"2025093006001136000_2025.09.22.25335736v1.13","doi-asserted-by":"publisher","DOI":"10.1016\/j.jstrokecerebrovasdis.2005.07.001"},{"key":"2025093006001136000_2025.09.22.25335736v1.14","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.60.3.400"},{"key":"2025093006001136000_2025.09.22.25335736v1.15","doi-asserted-by":"crossref","unstructured":"Sarfo FS , Akinyemi J , Akpalu A , et al. Frequency and factors associated with post-stroke seizures in a large multicenter study in West Africa. J Neurol Sci 2021; 427.","DOI":"10.1016\/j.jns.2021.117535"},{"key":"2025093006001136000_2025.09.22.25335736v1.16","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1002\/epi4.12103","article-title":"Early EEG predicts poststroke epilepsy","volume":"3","year":"2018","journal-title":"Epilepsia Open"},{"issue":"4","key":"2025093006001136000_2025.09.22.25335736v1.17","doi-asserted-by":"crossref","first-page":"558","DOI":"10.1002\/acn3.51534","article-title":"Acute epileptiform abnormalities are the primary predictors of post-stroke epilepsy: a matched, case-control study","volume":"9","year":"2022","journal-title":"Ann Clin Transl Neurol"},{"key":"2025093006001136000_2025.09.22.25335736v1.18","doi-asserted-by":"publisher","DOI":"10.1002\/ana.26212"},{"issue":"1","key":"2025093006001136000_2025.09.22.25335736v1.19","first-page":"e16074","article-title":"Prognostic value of early electrographic biomarkers of epileptogenesis in high-risk ischaemic stroke patients","volume":"31","year":"2023","journal-title":"Eur J Neurol"},{"key":"2025093006001136000_2025.09.22.25335736v1.20","doi-asserted-by":"publisher","DOI":"10.1002\/ana.27301"},{"key":"2025093006001136000_2025.09.22.25335736v1.21","doi-asserted-by":"crossref","first-page":"605","DOI":"10.1001\/jamaneurol.2023.0611","article-title":"Association of mortality and risk of epilepsy with type of acute symptomatic seizure after ischemic stroke and an updated prognostic model","volume":"80","year":"2023","journal-title":"JAMA Neurol"},{"key":"2025093006001136000_2025.09.22.25335736v1.22","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1001\/jamaneurol.2019.3485","article-title":"Development of Expert-Level Automated Detection of Epileptiform Discharges during Electroencephalogram Interpretation","volume":"77","year":"2020","journal-title":"JAMA Neurol"},{"key":"2025093006001136000_2025.09.22.25335736v1.23","doi-asserted-by":"publisher","DOI":"10.1136\/jnnp-2022-329542"},{"key":"2025093006001136000_2025.09.22.25335736v1.24","doi-asserted-by":"publisher","DOI":"10.1161\/01.STR.0000047852.05842.3C"},{"key":"2025093006001136000_2025.09.22.25335736v1.25","doi-asserted-by":"publisher","DOI":"10.1097\/CCM.0000000000004246"},{"key":"2025093006001136000_2025.09.22.25335736v1.26","doi-asserted-by":"publisher","DOI":"10.1111\/epi.12550"},{"key":"2025093006001136000_2025.09.22.25335736v1.27","doi-asserted-by":"publisher","DOI":"10.1161\/01.str.24.1.35"},{"key":"2025093006001136000_2025.09.22.25335736v1.28","doi-asserted-by":"publisher","DOI":"10.1016\/j.jneumeth.2020.108966"},{"key":"2025093006001136000_2025.09.22.25335736v1.29","doi-asserted-by":"publisher","DOI":"10.1097\/WNP.0000000000000493"},{"key":"2025093006001136000_2025.09.22.25335736v1.30","first-page":"841","article-title":"Random survival forests","volume":"2","year":"2008","journal-title":"Annals of Applied Statistics"},{"key":"2025093006001136000_2025.09.22.25335736v1.31","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2012.09.017"},{"key":"2025093006001136000_2025.09.22.25335736v1.32","doi-asserted-by":"publisher","DOI":"10.1093\/biostatistics\/kxu010"},{"key":"2025093006001136000_2025.09.22.25335736v1.33","doi-asserted-by":"crossref","unstructured":"Blanche P , Latouche A , Viallon V. Time-dependent AUC with right-censored data: A survey. In: Lecture Notes in Statistics. Springer Science and Business Media, LLC, 2015: 239\u201351.","DOI":"10.1007\/978-1-4614-8981-8_11"},{"key":"2025093006001136000_2025.09.22.25335736v1.34","first-page":"1","article-title":"A unified approach to interpreting model predictions","volume":"2","year":"2017","journal-title":"Nat Mach Intell"},{"key":"2025093006001136000_2025.09.22.25335736v1.35","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1055\/s-0043-1767764","article-title":"Specificity and sensitivity of the SeLECT score in predicting late seizures in patients undergoing intravenous thrombolytic treatment and the effect of diabetes mellitus and leukoaraiosis","volume":"81","year":"2023","journal-title":"Arq Neuropsiquiatr"},{"key":"2025093006001136000_2025.09.22.25335736v1.36","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1002\/ana.26497","article-title":"Association of Cortical Superficial Siderosis with Post-Stroke Epilepsy","volume":"93","year":"2023","journal-title":"Ann Neurol"},{"key":"2025093006001136000_2025.09.22.25335736v1.37","doi-asserted-by":"crossref","first-page":"806","DOI":"10.1177\/1747493018783759","article-title":"Baseline NIH Stroke Scale is an inferior predictor of functional outcome in the era of acute stroke intervention","volume":"13","year":"2018","journal-title":"Int J Stroke"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.09.22.25335736","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T20:46:36Z","timestamp":1768509996000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.1101\/2025.09.22.25335736"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,27]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1101\/2025.09.22.25335736","relation":{},"subject":[],"published":{"date-parts":[[2025,9,27]]},"subtype":"preprint"}}