Distinct Predictive and Recovery EEG Biomarkers of Motor Function after Noninvasive Brain Stimulation in Subacute Stroke Patients

Distinct Predictive and Recovery EEG Biomarkers of Motor Function after Noninvasive Brain Stimulation in Subacute Stroke Patients | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Distinct Predictive and Recovery EEG Biomarkers of Motor Function after Noninvasive Brain Stimulation in Subacute Stroke Patients Hyejeong Han, Yerim Huh, Sang Wook Lee, Yun-Hee Kim, Minji Lee This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9648366/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 4 You are reading this latest preprint version Abstract Background: Electroencephalography (EEG) has emerged as a promising biomarker for predicting motor recovery in stroke patients undergoing non-invasive brain stimulation (NIBS), including repetitive transcranial magnetic stimulation and transcranial direct current stimulation. However, it remains unclear whether baseline EEG features that account for between-subject variability in treatment responsiveness also capture within-subject neural changes associated with motor recovery over time. This study investigated whether pre-dictive EEG biomarkers and recovery-related EEG changes represent distinct neural mechanisms. Methods: Twelve patients with subacute stroke received dual-mode NIBS and were classified as responders (n = 7) or non-responders (n = 5) based on changes in the Fugl–Meyer Assessment Upper Extremity (FMA-UE) score two 1 months after stimulation. Baseline EEG features, including power spectral density (PSD), phase-locking value (PLV), and coherence (COH), were used to train multiple machine learning models to predict treatment responsiveness. Model performance was evaluated using 10-fold cross-validation. Longitudinal statistical analyses were conducted to examine associations between EEG changes across visits and motor recovery. Results: PSD-based models achieved the highest classification performance, with LightGBM yielding the best overall accuracy. Permutation importance analysis identified beta-band power at the ipsilesional T3 channel as the most influential baseline feature. In contrast, longitudinal analyses revealed a distinct pattern. Only changes in relative spectral power were significantly associated with motor recovery, with relative delta power changes at the ipsilesional O1 channel showing a significant correlation with improvements in FMA-UE scores (p < 0.05). No significant associations were observed for absolute or log-transformed power measures. Conclusions: Baseline treatment responsiveness and subsequent motor recovery were characterized by distinct neurophysiological signatures. Beta-band power at the ipsilesional T3 region may serve as a predictive biomarker of treatment response, whereas longitudinal changes in relative delta power at the ipsilesional O1 region were associated with recovery-related cortical reorganization. These findings support a framework that distinguishes predictive biomarkers from recovery-tracking biomarkers and may improve the interpretability of EEG-based prognostic models for stroke rehabilitation. Trial registration: Not applicable. Stroke Noninvasive brain stimulation Electroencephalography Motor recovery EEG biomarkers Neuroplasticity Longitudinal analysis Full Text Additional Declarations No competing interests reported. Supplementary Files JNER2026YRHuhHJHanSupplementarymaterial.pdf Cite Share Download PDF Status: Under Review Version 1 posted Reviewers invited by journal 14 May, 2026 Editor assigned by journal 09 May, 2026 Submission checks completed at journal 08 May, 2026 First submitted to journal 07 May, 2026 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-9648366","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":640344223,"identity":"9306876b-d43c-42f2-b282-066727a08856","order_by":0,"name":"Hyejeong Han","email":"","orcid":"","institution":"The Catholic University of Korea","correspondingAuthor":false,"prefix":"","firstName":"Hyejeong","middleName":"","lastName":"Han","suffix":""},{"id":640344224,"identity":"620068b9-9328-44bd-986e-fbb78f80ae1a","order_by":1,"name":"Yerim Huh","email":"","orcid":"","institution":"The Catholic University of Korea","correspondingAuthor":false,"prefix":"","firstName":"Yerim","middleName":"","lastName":"Huh","suffix":""},{"id":640344225,"identity":"36e0a50b-7a13-4de3-b194-75e35fbe432c","order_by":2,"name":"Sang Wook Lee","email":"","orcid":"","institution":"The Catholic University of America","correspondingAuthor":false,"prefix":"","firstName":"Sang","middleName":"Wook","lastName":"Lee","suffix":""},{"id":640344226,"identity":"65c0ddf9-130c-4cf4-9d59-b4ab0244eed3","order_by":3,"name":"Yun-Hee Kim","email":"","orcid":"","institution":"Myongji Choonhey Rehabilitation Hospital","correspondingAuthor":false,"prefix":"","firstName":"Yun-Hee","middleName":"","lastName":"Kim","suffix":""},{"id":640344227,"identity":"ace63318-1d9f-4dde-b762-237a17e0e957","order_by":4,"name":"Minji Lee","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA70lEQVRIiWNgGAWjYDACZgYGg4QCBgZ+CNuCByJ8gJAWAwYGyQYGxmYGBgkitIABUIvBAYgWBoJadNt5DxQ8MLCRMz5++PnjggoJGf4G5ocfGM7cw6nF7DBfAtBhacZmZ9IMm2eckeCROMBmLMFwoxiPFh4DoJbDidtuMBg287ZJ8AAdacbA8CGBkJb/9ZtnsH+EamH/RoyWAwkGEjwwW3iAttwgqCXZcMaZnMLZPCC/HOYplkg4g0fL+TNmhj8q7OT5249v+MxTYWPP396+8cOHY7i1AAGbASofGLkMeDUAlTzALz8KRsEoGAUjHgAAX/5LoxIOUYYAAAAASUVORK5CYII=","orcid":"","institution":"The Catholic University of Korea","correspondingAuthor":true,"prefix":"","firstName":"Minji","middleName":"","lastName":"Lee","suffix":""}],"badges":[],"createdAt":"2026-05-08 03:39:57","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9648366/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9648366/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":109405771,"identity":"d0af47f3-3dfe-49b8-aac2-8fccefee139a","added_by":"auto","created_at":"2026-05-17 13:20:09","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1086602,"visible":true,"origin":"","legend":"","description":"","filename":"JNER2026YRHuhHJHan.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9648366/v1_covered_df0b5a93-e3ba-4bb2-8e14-75082848ce4a.pdf"},{"id":109335526,"identity":"c2085906-bbb0-42c2-be4b-71a088c3c81a","added_by":"auto","created_at":"2026-05-15 17:04:19","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":79413,"visible":true,"origin":"","legend":"","description":"","filename":"JNER2026YRHuhHJHanSupplementarymaterial.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9648366/v1/e826539587bb279b603f1260.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Distinct Predictive and Recovery EEG Biomarkers of Motor Function after Noninvasive Brain Stimulation in Subacute Stroke Patients","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"journal-of-neuroengineering-and-rehabilitation","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jner","sideBox":"Learn more about [Journal of NeuroEngineering and Rehabilitation](http://jneuroengrehab.biomedcentral.com/)","snPcode":"12984","submissionUrl":"https://submission.nature.com/new-submission/12984/3","title":"Journal of NeuroEngineering and Rehabilitation","twitterHandle":"@BioMedCentral","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Stroke, Noninvasive brain stimulation, Electroencephalography, Motor recovery, EEG biomarkers, Neuroplasticity, Longitudinal analysis","lastPublishedDoi":"10.21203/rs.3.rs-9648366/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9648366/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eBackground: Electroencephalography (EEG) has emerged as a promising biomarker for predicting motor recovery in stroke patients undergoing non-invasive brain stimulation (NIBS), including repetitive transcranial magnetic stimulation and transcranial direct current stimulation. However, it remains unclear whether baseline EEG features that account for between-subject variability in treatment responsiveness also capture within-subject neural changes associated with motor recovery over time. This study\u0026nbsp;investigated whether pre-dictive EEG biomarkers and recovery-related EEG changes represent distinct neural mechanisms.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eMethods: Twelve patients with subacute stroke received dual-mode NIBS and were classified as responders (n = 7) or non-responders (n = 5) based on changes in the Fugl–Meyer Assessment Upper Extremity (FMA-UE) score two 1 months after stimulation. Baseline EEG features, including power spectral density (PSD), phase-locking value (PLV), and coherence (COH), were used to train multiple machine learning models to predict treatment responsiveness. Model performance was evaluated using 10-fold cross-validation. Longitudinal statistical analyses were conducted to examine associations between EEG changes across visits and motor recovery.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eResults: PSD-based models achieved the highest classification performance, with LightGBM yielding the best overall accuracy. Permutation importance analysis identified beta-band power at the ipsilesional T3 channel as the most influential baseline feature. In contrast, longitudinal analyses revealed a distinct pattern. Only changes in relative spectral power were significantly associated with motor recovery, with relative delta power changes at the ipsilesional O1 channel showing a significant correlation with improvements in FMA-UE scores (p \u0026lt; 0.05). No significant associations were observed for absolute or log-transformed power measures.\u0026nbsp;\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eConclusions: Baseline treatment responsiveness and subsequent motor recovery were characterized by distinct neurophysiological signatures. Beta-band power at the ipsilesional T3 region may serve as a predictive biomarker of treatment response, whereas longitudinal changes in relative delta power at the ipsilesional O1 region were associated with recovery-related cortical reorganization. These findings support a framework that distinguishes predictive biomarkers from recovery-tracking biomarkers and may improve the interpretability of EEG-based prognostic models for stroke rehabilitation.\u0026nbsp;\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eTrial registration: Not applicable.\u003c/p\u003e","manuscriptTitle":"Distinct Predictive and Recovery EEG Biomarkers of Motor Function after Noninvasive Brain Stimulation in Subacute Stroke Patients","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-15 17:04:15","doi":"10.21203/rs.3.rs-9648366/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewersInvited","content":"","date":"2026-05-14T07:01:04+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-05-09T05:41:51+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-05-08T14:25:05+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of NeuroEngineering and Rehabilitation","date":"2026-05-08T03:29:28+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"journal-of-neuroengineering-and-rehabilitation","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jner","sideBox":"Learn more about [Journal of NeuroEngineering and Rehabilitation](http://jneuroengrehab.biomedcentral.com/)","snPcode":"12984","submissionUrl":"https://submission.nature.com/new-submission/12984/3","title":"Journal of NeuroEngineering and Rehabilitation","twitterHandle":"@BioMedCentral","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"271c4f4a-750e-4e99-9c4b-83f641c96ede","owner":[],"postedDate":"May 15th, 2026","published":true,"recentEditorialEvents":[{"type":"reviewersInvited","content":"10","date":"2026-05-14T07:01:04+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-05-09T05:41:51+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-05-08T14:25:05+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of NeuroEngineering and Rehabilitation","date":"2026-05-08T03:29:28+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-15T17:04:15+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-15 17:04:15","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9648366","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9648366","identity":"rs-9648366","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}