Advanced Brain Age Prediction Using Multi-Head Self-Attention: A Comparative Analysis of Western and Middle Eastern MRI Datasets

Advanced Brain Age Prediction Using Multi-Head Self-Attention: A Comparative Analysis of Western and Middle Eastern MRI Datasets | 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 Advanced Brain Age Prediction Using Multi-Head Self-Attention: A Comparative Analysis of Western and Middle Eastern MRI Datasets Matin Irajpour, Majid Barekatain, Mahdieh Karami, Shaghayegh Karimi Alavijeh, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6342594/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 Brain age estimation is a critical biomarker for early detection of neurodegenerative diseases, but existing models are primarily trained on Western datasets, limiting their applicability to diverse populations. Recent studies suggest that brain aging patterns vary across ethnic groups, highlighting the need for more inclusive and adaptable AI-driven neuroimaging models. We trained our model on 4,635 healthy individuals (40--80 years) from ADNI, OASIS-3, Cam-CAN, and IXI, using 80% of data (n=3700) for training and 20% (n=935) for testing. The model was further tested on a Middle Eastern dataset (107 subjects, Tehran, Iran). It integrates multi-head self-attention along with residual connections to enhance long-range spatial feature learning, improving upon previous CNN models. Performance was evaluated using mean absolute error (MAE). The model achieved state-of-the-art accuracy (MAE = 1.99 years) on the Western test set, while being much lighter than previous models (approximately 3 million parameters); however, it performed significantly worse on the ME dataset (best MAE = 4.35 years, final = 5.83 years). Bias correction did not improve performance, indicating population-specific brain aging differences. These findings emphasize the need for diverse training datasets and cross-population adaptation techniques. Biological sciences/Computational biology and bioinformatics/Image processing Biological sciences/Computational biology and bioinformatics/Machine learning Health sciences/Medical research Health sciences/Neurology Brain Age CNN Multi-head Self-Attention Neuroimaging ethnic differences Magnetic Resonance Imaging Neurodegeneration normal aging Full Text Additional Declarations No competing interests reported. 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-6342594","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":436175695,"identity":"700531c6-f852-4a78-93d5-fb31a18a9661","order_by":0,"name":"Matin Irajpour","email":"","orcid":"","institution":"Institute for Cognitive Science Studies","correspondingAuthor":false,"prefix":"","firstName":"Matin","middleName":"","lastName":"Irajpour","suffix":""},{"id":436175696,"identity":"2675b1e9-3706-4411-884a-ed32008f06eb","order_by":1,"name":"Majid Barekatain","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA30lEQVRIiWNgGAWjYBACAyBmbAASbAzMByAsIrUYALWwJZCohYGBx4A4LebsZx8+nFHzR55PuuebxM8dNnIM7IePbsCnxbIn3dhwwzEDwzaZs9ske8+kGTPwpKXdwOuwA2lskg/YDBjbJHK3SfC2HU5skOAxw6/l/DP2nw/+Gdi3SeQ8k/xLlJYbaWyMG9sMEoFa2KSJssVyxjNmyZl9xsltEmnG1rJtacZshPxizp/G+LHnm5zt/BnJD2++bbOR42c/fAyvFmTAIgEi2YhVDgLMH0hRPQpGwSgYBSMHAABX2UkH3yIKVwAAAABJRU5ErkJggg==","orcid":"","institution":"Institute for Cognitive Science Studies","correspondingAuthor":true,"prefix":"","firstName":"Majid","middleName":"","lastName":"Barekatain","suffix":""},{"id":436175697,"identity":"661b204a-c3fa-437b-8d73-fa89dc516f77","order_by":2,"name":"Mahdieh Karami","email":"","orcid":"","institution":"Institute for Cognitive Science Studies","correspondingAuthor":false,"prefix":"","firstName":"Mahdieh","middleName":"","lastName":"Karami","suffix":""},{"id":436175698,"identity":"9b061e1a-5431-41c4-8204-53b694a40657","order_by":3,"name":"Shaghayegh Karimi Alavijeh","email":"","orcid":"","institution":"Tehran University of Medical Sciences","correspondingAuthor":false,"prefix":"","firstName":"Shaghayegh","middleName":"Karimi","lastName":"Alavijeh","suffix":""},{"id":436175699,"identity":"a7474966-19a8-419d-bef4-57210af088b2","order_by":4,"name":"Mohammad Barekatain","email":"","orcid":"","institution":"Sharif University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Mohammad","middleName":"","lastName":"Barekatain","suffix":""},{"id":436175700,"identity":"6e251981-a601-4049-996b-f96146fb1b2d","order_by":5,"name":"Masih Irajpour","email":"","orcid":"","institution":"Isfahan University of Medical Sciences","correspondingAuthor":false,"prefix":"","firstName":"Masih","middleName":"","lastName":"Irajpour","suffix":""}],"badges":[],"createdAt":"2025-03-31 07:39:50","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-6342594/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6342594/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":84322305,"identity":"a21a25de-b10e-4def-a5b3-c64bdd9b83d1","added_by":"auto","created_at":"2025-06-10 14:32:16","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1046618,"visible":true,"origin":"","legend":"","description":"","filename":"latex.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6342594/v1_covered_a5807fc7-430e-4a58-a05d-97d09317825f.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Advanced Brain Age Prediction Using Multi-Head Self-Attention: A Comparative Analysis of Western and Middle Eastern MRI Datasets","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":true,"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":"Brain Age, CNN, Multi-head, Self-Attention, Neuroimaging ethnic differences, Magnetic Resonance Imaging, Neurodegeneration normal aging","lastPublishedDoi":"10.21203/rs.3.rs-6342594/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6342594/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eBrain age estimation is a critical biomarker for early detection of neurodegenerative diseases, but existing models are primarily trained on Western datasets, limiting their applicability to diverse populations. Recent studies suggest that brain aging patterns vary across ethnic groups, highlighting the need for more inclusive and adaptable AI-driven neuroimaging models. We trained our model on 4,635 healthy individuals (40--80 years) from ADNI, OASIS-3, Cam-CAN, and IXI, using 80% of data (n=3700) for training and 20% (n=935) for testing. The model was further tested on a Middle Eastern dataset (107 subjects, Tehran, Iran). It integrates multi-head self-attention along with residual connections to enhance long-range spatial feature learning, improving upon previous CNN models. Performance was evaluated using mean absolute error (MAE). The model achieved state-of-the-art accuracy (MAE = 1.99 years) on the Western test set, while being much lighter than previous models (approximately 3 million parameters); however, it performed significantly worse on the ME dataset (best MAE = 4.35 years, final = 5.83 years). Bias correction did not improve performance, indicating population-specific brain aging differences. These findings emphasize the need for diverse training datasets and cross-population adaptation techniques.\u0026nbsp;\u003c/p\u003e","manuscriptTitle":"Advanced Brain Age Prediction Using Multi-Head Self-Attention: A Comparative Analysis of Western and Middle Eastern MRI Datasets","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-08 06:46:24","doi":"10.21203/rs.3.rs-6342594/v1","editorialEvents":[{"type":"communityComments","content":0}],"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":"452a7611-09de-41af-a0ac-72280d197686","owner":[],"postedDate":"April 8th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":46830238,"name":"Biological sciences/Computational biology and bioinformatics/Image processing"},{"id":46830239,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"},{"id":46830240,"name":"Health sciences/Medical research"},{"id":46830241,"name":"Health sciences/Neurology"}],"tags":[],"updatedAt":"2025-06-10T14:24:02+00:00","versionOfRecord":[],"versionCreatedAt":"2025-04-08 06:46:24","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6342594","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6342594","identity":"rs-6342594","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}