Artificial intelligence reveals neural features below statistical threshold in ADHD face recognition

Artificial intelligence reveals neural features below statistical threshold in ADHD face recognition | 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 Artificial intelligence reveals neural features below statistical threshold in ADHD face recognition Zhikai Yu, Zijian Zhou, Yaoyao Li, Changming Wang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9238004/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Current ADHD diagnosis lacks objective neural biomarkers. Traditional ERP analysis, based on group-mean comparisons, is insensitive to signals with high trial-by-trial variability. We recorded 128-channel EEG from 102 ADHD and 49 control participants during a face matching task, applying a five-modality framework: ERP, time-frequency (ITPC), functional connectivity (PLI), deep learning (CNN and Transformer), and explainable AI (Grad-CAM and attention weights). Conventional statistics identified significant differences in P1, N1, N170, and P300. Critically, an ablation study showed that EEG restricted to non-significant components (P2, N2, Central-Late) still achieved AUC=0.733-0.782, directly falsifying the assumption that non-significance implies no diagnostic value. Grad-CAM and Transformer attention independently converged on 150-300 ms as the core discriminative window. Reduced ITPC in ADHD explains why these features evade conventional statistics. AI-assisted analysis systematically uncovers neural biomarkers invisible to group-mean approaches. Health sciences/Biomarkers/Diagnostic markers Physical sciences/Engineering/Biomedical engineering ADHD Event-Related Potential Deep Learning Explainable AI Face Recognition Neural Biomarker Full Text Additional Declarations There is NO Competing Interest. Cite Share Download PDF Status: Posted Version 1 posted 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-9238004","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":626473892,"identity":"7ba5c920-0ef6-41dc-8c2a-c9b75d8e86bc","order_by":0,"name":"Zhikai Yu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA0klEQVRIie3QMQrCMBTG8SeF6BDpJi849AophaLQw+jeQXAXXeLiAVoEvYJujpW3FlwVl4Lg3LHdbJ2c2rgJ5r8Fvh8hATCZfrXOEiVYVpLkxXeETc/xRp+ABOAe9ZjGWl5DX5SnkWeveU7AwbEHSTMRUeijSNFH6h9oNgI33k6aiT2siKswgJpEHCby3kJYTaYVcYhnxJkGed9yVuhL4qBHxP45H68Uei4xWX0ytr9FpnS8lWrh7i70yPMicOxhCwHoyc8Tts3rupnOymQymf65F3VHQQCrQ4k8AAAAAElFTkSuQmCC","orcid":"https://orcid.org/0009-0005-4985-4036","institution":"University College London","correspondingAuthor":true,"prefix":"","firstName":"Zhikai","middleName":"","lastName":"Yu","suffix":""},{"id":626473893,"identity":"2e52f6d4-67d3-4351-b0a9-aa277fea16a1","order_by":1,"name":"Zijian Zhou","email":"","orcid":"","institution":"Huabei University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Zijian","middleName":"","lastName":"Zhou","suffix":""},{"id":626473894,"identity":"93e6257f-9bd7-44d0-b9d2-844218bea07c","order_by":2,"name":"Yaoyao Li","email":"","orcid":"","institution":"School of Nursing, Peking University","correspondingAuthor":false,"prefix":"","firstName":"Yaoyao","middleName":"","lastName":"Li","suffix":""},{"id":626473895,"identity":"25d43131-5e91-4205-8a44-e40790b3ad94","order_by":3,"name":"Changming Wang","email":"","orcid":"","institution":"Capital Medical University","correspondingAuthor":false,"prefix":"","firstName":"Changming","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2026-03-26 21:00:47","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9238004/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9238004/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108181174,"identity":"c19367f4-3dd9-46d6-8c68-701a4e77bd6f","added_by":"auto","created_at":"2026-04-30 08:58:12","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2061490,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript260326v1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9238004/v1_covered_852676f5-4b3d-40ab-9e92-52cd53255028.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Artificial intelligence reveals neural features below statistical threshold in ADHD face recognition","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"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":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"ADHD, Event-Related Potential, Deep Learning, Explainable AI, Face Recognition, Neural Biomarker","lastPublishedDoi":"10.21203/rs.3.rs-9238004/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9238004/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Current ADHD diagnosis lacks objective neural biomarkers. Traditional ERP analysis, based on group-mean comparisons, is insensitive to signals with high trial-by-trial variability. We recorded 128-channel EEG from 102 ADHD and 49 control participants during a face matching task, applying a five-modality framework: ERP, time-frequency (ITPC), functional connectivity (PLI), deep learning (CNN and Transformer), and explainable AI (Grad-CAM and attention weights). Conventional statistics identified significant differences in P1, N1, N170, and P300. Critically, an ablation study showed that EEG restricted to non-significant components (P2, N2, Central-Late) still achieved AUC=0.733-0.782, directly falsifying the assumption that non-significance implies no diagnostic value. Grad-CAM and Transformer attention independently converged on 150-300 ms as the core discriminative window. Reduced ITPC in ADHD explains why these features evade conventional statistics. AI-assisted analysis systematically uncovers neural biomarkers invisible to group-mean approaches.","manuscriptTitle":"Artificial intelligence reveals neural features below statistical threshold in ADHD face recognition","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-28 19:21:14","doi":"10.21203/rs.3.rs-9238004/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"010dd1b7-6a29-4b1f-afdf-fb194fcd3dd4","owner":[],"postedDate":"April 28th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":66675376,"name":"Health sciences/Biomarkers/Diagnostic markers"},{"id":66675377,"name":"Physical sciences/Engineering/Biomedical engineering"}],"tags":[],"updatedAt":"2026-04-28T19:21:14+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-28 19:21:14","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9238004","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9238004","identity":"rs-9238004","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}