Physics-Informed Neural Networks for Robust Digital Biomarker Discovery in Low-Density Wearable EEG Systems

Physics-Informed Neural Networks for Robust Digital Biomarker Discovery in Low-Density Wearable EEG Systems | 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 Article Physics-Informed Neural Networks for Robust Digital Biomarker Discovery in Low-Density Wearable EEG Systems Emmanuel Lwele, Francis Chikweto This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9455997/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 7 You are reading this latest preprint version Abstract Background: Wearable electroencephalography (EEG) holds transformative potential for community-based neurological diagnosis, yet the translation from hospital-grade 23-channel recordings to low-density, motion-corrupted wearable signals introduces severe domain shift that invalidates conventional machine-learning biomarkers. Thousands of patients with suspected seizures face diagnostic waits exceeding twelve months, with up to 30% subsequently reclassified between epilepsy, functional neurological disorder (FND), and other non-epileptic conditions. Methods: We propose a Physics-Informed Neural Network (PINN) framework for robust EEG biomarker learning that couples a graph neural network (GNN) spatial encoder with a bidirectional LSTM temporal encoder and four physiologically grounded loss components: a spectral constraint ( L spec ), a spatial diffusion constraint ( L spat ), a functional connectivity stability constraint ( L conn ), and a novel biomarker stability constraint ( L bio ). The framework is validated on the CHB-MIT Scalp EEG Database (subject chb21; four annotated seizures), with a synthetic degradation pipeline simulating electrode dropout (23 → 4 channels), Gaussian noise (σ ∈ [0.1, 2.0]×SD), motion artefacts, and downsampling (256→64 Hz). Strict leave-one-patient-out cross-validation was employed throughout. Results: Under hospital-grade conditions the PINN-GNN achieved AUROC = 0.972 and F1 = 0.954 for seizure detection. Under extreme wearable-grade degradation (σ = 2.0) the PINN-GNN retained AUROC = 0.881, compared with 0.741 for a baseline GNN,a 16.2% relative robustness improvement. The biomarker stability index (BSI) was significantly lower for the PINN-GNN across all six biomarker classes tested (band power ratio, spectral entropy, phase-locking value, graph centrality, Hjorth mobility, and theta coherence; p < 0.001 in each case). Three-dimensional functional connectivity matrices revealed ictal hyperconnectivity that was recoverable under wearable degradation when physics constraints were active. Conclusions: Physics-informed constraints substantially improve EEG biomarker stability under real-world degradation conditions, advancing the feasibility of community-based seizure monitoring. The proposed framework directly addresses the EPSRC-funded research mandate to develop and validate robust biomarkers for wearable EEG deployment in epilepsy, FND, and related conditions, and provides a validated methodological foundation for differentiation of epilepsy, FND, and syncope from low-density EEG data. Health sciences/Biomarkers Biological sciences/Computational biology and bioinformatics Physical sciences/Engineering Health sciences/Neurology Biological sciences/Neuroscience digital biomarkers physics-informed neural networks wearable EEG seizure detection graph neural networks domain adaptation CHB-MIT functional connectivity epilepsy functional neurological disorder Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 18 May, 2026 Reviewers agreed at journal 03 May, 2026 Reviewers agreed at journal 27 Apr, 2026 Reviewers invited by journal 22 Apr, 2026 Editor assigned by journal 21 Apr, 2026 Submission checks completed at journal 21 Apr, 2026 First submitted to journal 18 Apr, 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-9455997","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":630450828,"identity":"daa75cf0-d2ec-41ee-a45a-4b1cdd9f0fa9","order_by":0,"name":"Emmanuel Lwele","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAzUlEQVRIiWNgGAWjYFAC5gYGhgIGOQYJKF8Cn2IIYARqMWAwJl1LYgPRWvgZGNskPhjYpM+f3WPA8KOGIXFmAwEtkg2MbZIzDNJyN9w5Y8DYc4whcTYhWwwOMLbd5jE4nLtBIseAgbeBIXEeIS32IC1/DP6ny8/IMWD8S4wWA6BfbgPtSmC4kWPADLKFoMMkDjO2/+wxSDbccCOt4LDMMQljgt7nb28+bPCjwk5efkbyxodvamxkZxwgZA0zEvsAURE5CkbBKBgFo4AwAABI8jv3a7C0KQAAAABJRU5ErkJggg==","orcid":"","institution":"Sheffield Hallam University","correspondingAuthor":true,"prefix":"","firstName":"Emmanuel","middleName":"","lastName":"Lwele","suffix":""},{"id":630450830,"identity":"e25fb80d-3dcb-457d-9322-a9151278be47","order_by":1,"name":"Francis Chikweto","email":"","orcid":"","institution":"Tohoku University","correspondingAuthor":false,"prefix":"","firstName":"Francis","middleName":"","lastName":"Chikweto","suffix":""}],"badges":[],"createdAt":"2026-04-18 10:53:57","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9455997/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9455997/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108006620,"identity":"4384b6c4-1e41-45ca-b3e9-f6502af2d5ff","added_by":"auto","created_at":"2026-04-28 12:56:10","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3264339,"visible":true,"origin":"","legend":"","description":"","filename":"PhysicsInformedNeuralNetworksforRobustDigitalBiomarkerDiscoveryinLowDensityWearableEEGSystems.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9455997/v1_covered_e29fed4d-77ec-4476-af90-c1175ba4b250.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Physics-Informed Neural Networks for Robust Digital Biomarker Discovery in Low-Density Wearable EEG Systems","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":"npj-digital-medicine","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"npjdigitalmed","sideBox":"Learn more about [npj Digital Medicine](http://www.nature.com/npjdigitalmed/)","snPcode":"41746","submissionUrl":"https://submission.springernature.com/new-submission/41746/3","title":"npj Digital Medicine","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"digital biomarkers, physics-informed neural networks, wearable EEG, seizure detection, graph neural networks, domain adaptation, CHB-MIT, functional connectivity, epilepsy, functional neurological disorder ","lastPublishedDoi":"10.21203/rs.3.rs-9455997/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9455997/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003eBackground:\u003c/strong\u003e Wearable electroencephalography (EEG) holds transformative potential for community-based neurological diagnosis, yet the translation from hospital-grade 23-channel recordings to low-density, motion-corrupted wearable signals introduces severe domain shift that invalidates conventional machine-learning biomarkers. Thousands of patients with suspected seizures face diagnostic waits exceeding twelve months, with up to 30% subsequently reclassified between epilepsy, functional neurological disorder (FND), and other non-epileptic conditions.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eMethods:\u003c/strong\u003e We propose a Physics-Informed Neural Network (PINN) framework for robust EEG biomarker learning that couples a graph neural network (GNN) spatial encoder with a bidirectional LSTM temporal encoder and four physiologically grounded loss components: a spectral constraint (\u003cem\u003eL\u003c/em\u003e\u003csub\u003e\u003cem\u003espec\u003c/em\u003e\u003c/sub\u003e), a spatial diffusion constraint (\u003cem\u003eL\u003c/em\u003e\u003csub\u003e\u003cem\u003espat\u003c/em\u003e\u003c/sub\u003e), a functional connectivity stability constraint (\u003cem\u003eL\u003c/em\u003e\u003csub\u003e\u003cem\u003econn\u003c/em\u003e\u003c/sub\u003e), and a novel biomarker stability constraint (\u003cem\u003eL\u003c/em\u003e\u003csub\u003e\u003cem\u003ebio\u003c/em\u003e\u003c/sub\u003e). The framework is validated on the CHB-MIT Scalp EEG Database (subject chb21; four annotated seizures), with a synthetic degradation pipeline simulating electrode dropout (23 → 4 channels), Gaussian noise (σ ∈ [0.1, 2.0]×SD), motion artefacts, and downsampling (256→64 Hz). Strict leave-one-patient-out cross-validation was employed throughout.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eResults:\u003c/strong\u003e Under hospital-grade conditions the PINN-GNN achieved AUROC = 0.972 and F1 = 0.954 for seizure detection. Under extreme wearable-grade degradation (σ = 2.0) the PINN-GNN retained AUROC = 0.881, compared with 0.741 for a baseline GNN,a 16.2% relative robustness improvement. The biomarker stability index (BSI) was significantly lower for the PINN-GNN across all six biomarker classes tested (band power ratio, spectral entropy, phase-locking value, graph centrality, Hjorth mobility, and theta coherence; p \u0026lt; 0.001 in each case). Three-dimensional functional connectivity matrices revealed ictal hyperconnectivity that was recoverable under wearable degradation when physics constraints were active.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConclusions:\u003c/strong\u003e Physics-informed constraints substantially improve EEG biomarker stability under real-world degradation conditions, advancing the feasibility of community-based seizure monitoring. The proposed framework directly addresses the EPSRC-funded research mandate to develop and validate robust biomarkers for wearable EEG deployment in epilepsy, FND, and related conditions, and provides a validated methodological foundation for differentiation of epilepsy, FND, and syncope from low-density EEG data.\u003c/p\u003e","manuscriptTitle":"Physics-Informed Neural Networks for Robust Digital Biomarker Discovery in Low-Density Wearable EEG Systems","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-28 10:27:36","doi":"10.21203/rs.3.rs-9455997/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-05-18T23:01:05+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"303159386484368538179177148933311971797","date":"2026-05-03T20:05:53+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"273800846518066823245244260611949094237","date":"2026-04-27T14:55:39+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-22T16:58:37+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-21T17:41:45+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-21T07:06:21+00:00","index":"","fulltext":""},{"type":"submitted","content":"npj Digital Medicine","date":"2026-04-18T10:47:02+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"npj-digital-medicine","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"npjdigitalmed","sideBox":"Learn more about [npj Digital Medicine](http://www.nature.com/npjdigitalmed/)","snPcode":"41746","submissionUrl":"https://submission.springernature.com/new-submission/41746/3","title":"npj Digital Medicine","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"a0de19b9-605f-4570-b850-aafac4493a7a","owner":[],"postedDate":"April 28th, 2026","published":true,"recentEditorialEvents":[{"type":"editorInvitedReview","content":"","date":"2026-05-18T23:01:05+00:00","index":33,"fulltext":""},{"type":"reviewerAgreed","content":"303159386484368538179177148933311971797","date":"2026-05-03T20:05:53+00:00","index":30,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":67102329,"name":"Health sciences/Biomarkers"},{"id":67102330,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":67102331,"name":"Physical sciences/Engineering"},{"id":67102332,"name":"Health sciences/Neurology"},{"id":67102333,"name":"Biological sciences/Neuroscience"}],"tags":[],"updatedAt":"2026-04-28T10:27:36+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-28 10:27:36","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9455997","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9455997","identity":"rs-9455997","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}