MRI-based and metabolomics-based age scores act synergetically for mortality prediction shown by multi-cohort federated learning

preprint OA: gold CC-BY-4.0
📄 Open PDF Full text JSON View at publisher
AI-generated deep summary by claude@2026-06, 2026-06-24 · read from full text

The paper evaluated associations between two biological age scores—BrainAge derived from brain MRI and MetaboAge derived from metabolomic biomarkers—by training a federated deep learning model across three cohorts and comparing federated versus locally trained performance. It found that the federated BrainAge model produced significantly lower age-prediction error than local models, and that harmonizing the age interval across cohorts improved BrainAge accuracy. In federated association and survival analyses, BrainAge and MetaboAge showed only a small association with each other, but combining them yielded higher predictive value for time to mortality than either score alone. This paper does not explicitly discuss endometriosis or adenomyosis; it was included in the corpus via a keyword match in the upstream search index.

Read from the paper's body, not the abstract. Not a substitute for reading the paper. No clinical advice. How this works

Full text 16,173 characters · extracted from preprint-html · click to expand
MRI-based and metabolomics-based age scores act synergetically for mortality prediction shown by multi-cohort federated learning | 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 MRI-based and metabolomics-based age scores act synergetically for mortality prediction shown by multi-cohort federated learning Esther Bron, Pedro Mateus, Swier Garst, Jing Yu, Davy Cats, Alexander Harms, and 16 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4938500/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 Biological age scores are an emerging tool to characterize aging by estimating chronological age based on physiological biomarkers. Various scores have shown associations with aging-related outcomes. This study assessed the relation between an age score based on brain MRI images (BrainAge) and an age score based on metabolomic biomarkers (MetaboAge). We trained a federated deep learning model to estimate BrainAge in three cohorts. The federated BrainAge model yielded significantly lower error for age prediction across the cohorts than locally trained models. Harmonizing the age interval between cohorts further improved BrainAge accuracy. Subsequently, we compared BrainAge with MetaboAge using federated association and survival analyses. The results showed a small association between BrainAge and MetaboAge as well as a higher predictive value for the time to mortality of both scores combined than for the individual scores. Hence, our study suggests that both aging scores capture different aspects of the aging process. Health sciences/Medical research/Biomarkers/Predictive markers Biological sciences/Biotechnology/Metabolomics Health sciences/Health care/Medical imaging/Brain imaging Physical sciences/Mathematics and computing/Computer science Full Text Additional Declarations (Not answered) Supplementary Files NCDCusecase1supplement.pdf 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-4938500","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":346954417,"identity":"04f147ac-bd25-4514-ac81-c9cb5ffbe679","order_by":0,"name":"Esther Bron","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAyUlEQVRIiWNgGAWjYFACHhBhgyzC3ECMljRkEUaitBwmQQs/A++xDx93nJczbz/+dDPPn23yDNKN+LVINvAlz5x55raxzJkcs9u8bbcNG2QO4tdicIDHmBmoMnEGQw7bbd6G2wkMEon4tdhDtJyrn8H//Nltnj9EaDFgAGs5kCAhkWB2m4eNCC0Sh/mSGWe2JRvOkHhjdnMu0C9thLTwt/ceZvjYZicvwZ/+7MabP7fl+SWSD+DVwsCMLsCGX/0oGAWjYBSMAmIAANKMQnczQXP4AAAAAElFTkSuQmCC","orcid":"https://orcid.org/0000-0002-5778-9263","institution":"Erasmus MC - university Medical Center Rotterdam","correspondingAuthor":true,"prefix":"","firstName":"Esther","middleName":"","lastName":"Bron","suffix":""},{"id":346954418,"identity":"f279ac3f-712b-445a-a530-0a61ee7fa595","order_by":1,"name":"Pedro Mateus","email":"","orcid":"","institution":"Maastricht University Medical Center","correspondingAuthor":false,"prefix":"","firstName":"Pedro","middleName":"","lastName":"Mateus","suffix":""},{"id":346954419,"identity":"449071db-86de-4a58-a66c-2d6fd9958faa","order_by":2,"name":"Swier Garst","email":"","orcid":"https://orcid.org/0009-0009-4774-0309","institution":"Delft University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Swier","middleName":"","lastName":"Garst","suffix":""},{"id":346954420,"identity":"e46b32f8-6715-4c77-8317-30c324dc911e","order_by":3,"name":"Jing Yu","email":"","orcid":"","institution":"Erasmus Medical Center","correspondingAuthor":false,"prefix":"","firstName":"Jing","middleName":"","lastName":"Yu","suffix":""},{"id":346954421,"identity":"902547a3-7b0d-4e1a-b0bc-28fab3d7db10","order_by":4,"name":"Davy Cats","email":"","orcid":"","institution":"Leiden University Medical Center","correspondingAuthor":false,"prefix":"","firstName":"Davy","middleName":"","lastName":"Cats","suffix":""},{"id":346954422,"identity":"57a99741-e984-4616-958c-d75a10cd00b4","order_by":5,"name":"Alexander Harms","email":"","orcid":"","institution":"Erasmus Medical Center","correspondingAuthor":false,"prefix":"","firstName":"Alexander","middleName":"","lastName":"Harms","suffix":""},{"id":346954423,"identity":"5fd4b690-447f-4f24-a8d9-261dd21ef98f","order_by":6,"name":"Mahlet Birhanu","email":"","orcid":"","institution":"Erasmus Medical Center","correspondingAuthor":false,"prefix":"","firstName":"Mahlet","middleName":"","lastName":"Birhanu","suffix":""},{"id":346954424,"identity":"1d7cbd0f-8541-46a4-8d1f-ddbcb69d1900","order_by":7,"name":"Marian Beekman","email":"","orcid":"","institution":"Leiden University Medical Center","correspondingAuthor":false,"prefix":"","firstName":"Marian","middleName":"","lastName":"Beekman","suffix":""},{"id":346954425,"identity":"db0159bc-d577-497a-b03f-bb2beadffa0d","order_by":8,"name":"Eline Slagboom","email":"","orcid":"","institution":"Leiden University Medical Center","correspondingAuthor":false,"prefix":"","firstName":"Eline","middleName":"","lastName":"Slagboom","suffix":""},{"id":346954426,"identity":"fbd12480-6ea3-493c-8dff-0790c205c378","order_by":9,"name":"Marcel Reinders","email":"","orcid":"https://orcid.org/0000-0002-1148-1562","institution":"Delft University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Marcel","middleName":"","lastName":"Reinders","suffix":""},{"id":346954427,"identity":"53e364ac-fe37-4a12-b193-48f8e8f00c3a","order_by":10,"name":"Jeroen van der Grond","email":"","orcid":"","institution":"Leiden University Medical Center","correspondingAuthor":false,"prefix":"","firstName":"Jeroen","middleName":"van der","lastName":"Grond","suffix":""},{"id":346954428,"identity":"8b990f89-3aea-4772-9037-6225cbaf4b63","order_by":11,"name":"Andre Dekker","email":"","orcid":"https://orcid.org/0000-0002-0422-7996","institution":"Maastricht University Medical Centre","correspondingAuthor":false,"prefix":"","firstName":"Andre","middleName":"","lastName":"Dekker","suffix":""},{"id":346954429,"identity":"ca2232e4-ef8a-400d-9c03-68d4bea06713","order_by":12,"name":"Jacobus Jansen","email":"","orcid":"","institution":"Maastricht University Medical Center","correspondingAuthor":false,"prefix":"","firstName":"Jacobus","middleName":"","lastName":"Jansen","suffix":""},{"id":346954430,"identity":"da82dfb7-d297-4335-af8a-2e7f8bd8dc3c","order_by":13,"name":"Magdalena Beran","email":"","orcid":"","institution":"Maastricht University","correspondingAuthor":false,"prefix":"","firstName":"Magdalena","middleName":"","lastName":"Beran","suffix":""},{"id":346954431,"identity":"0aa9b59b-3d28-4727-912c-532ea13dee58","order_by":14,"name":"Miranda Schram","email":"","orcid":"","institution":"Maastricht University Medical Center","correspondingAuthor":false,"prefix":"","firstName":"Miranda","middleName":"","lastName":"Schram","suffix":""},{"id":346954432,"identity":"700019d6-424c-4469-9ea8-c9a8de5870f1","order_by":15,"name":"Pieter Jelle Visser","email":"","orcid":"","institution":"Amsterdam UMC","correspondingAuthor":false,"prefix":"","firstName":"Pieter","middleName":"Jelle","lastName":"Visser","suffix":""},{"id":346954433,"identity":"65139b54-7145-49c0-acc8-a267a5d3ee21","order_by":16,"name":"Justine Moonen","email":"","orcid":"","institution":"Vrije Universiteit","correspondingAuthor":false,"prefix":"","firstName":"Justine","middleName":"","lastName":"Moonen","suffix":""},{"id":346954434,"identity":"580a0dae-2a93-482f-b0c8-c8f0dc6cb58d","order_by":17,"name":"Mohsen Ghanbari","email":"","orcid":"","institution":"Erasmus Medical Center","correspondingAuthor":false,"prefix":"","firstName":"Mohsen","middleName":"","lastName":"Ghanbari","suffix":""},{"id":346954435,"identity":"f94716b2-caf0-4f3e-9d3e-22cddb276a33","order_by":18,"name":"Gennady Roshchupkin","email":"","orcid":"https://orcid.org/0000-0002-3403-2313","institution":"Erasmus Medical Center","correspondingAuthor":false,"prefix":"","firstName":"Gennady","middleName":"","lastName":"Roshchupkin","suffix":""},{"id":346954436,"identity":"43c588f2-6878-46a3-bf12-958484e7ed71","order_by":19,"name":"Dina Vojinovic","email":"","orcid":"","institution":"IQVIA Nederland","correspondingAuthor":false,"prefix":"","firstName":"Dina","middleName":"","lastName":"Vojinovic","suffix":""},{"id":346954437,"identity":"bb79a90b-2ea1-400c-9620-ddff7f301475","order_by":20,"name":"Inigo Bermejo","email":"","orcid":"","institution":"Maastricht University Medical Center","correspondingAuthor":false,"prefix":"","firstName":"Inigo","middleName":"","lastName":"Bermejo","suffix":""},{"id":346954438,"identity":"9ace9091-a507-4a97-a728-9c3d47901d70","order_by":21,"name":"Hailiang Mei","email":"","orcid":"","institution":"Leiden University Medical Center","correspondingAuthor":false,"prefix":"","firstName":"Hailiang","middleName":"","lastName":"Mei","suffix":""}],"badges":[],"createdAt":"2024-08-19 12:00:55","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4938500/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4938500/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":64640517,"identity":"ba9ef54a-dd2b-4d15-8424-fe0ebdfd3a49","added_by":"auto","created_at":"2024-09-17 02:05:03","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":862076,"visible":true,"origin":"","legend":"","description":"","filename":"NCDCusecase1maintext.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4938500/v1_covered_0ab61f0c-91a5-4c84-8fb6-c6dff3731715.pdf"},{"id":64639674,"identity":"305c8eb0-d651-4d0c-9516-869b7bb3e917","added_by":"auto","created_at":"2024-09-17 01:49:00","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":3295052,"visible":true,"origin":"","legend":"","description":"","filename":"NCDCusecase1supplement.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4938500/v1/8fb6891a8d40b0db6655a746.pdf"}],"financialInterests":"(Not answered)","formattedTitle":"MRI-based and metabolomics-based age scores act synergetically for mortality prediction shown by multi-cohort federated learning","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":"","lastPublishedDoi":"10.21203/rs.3.rs-4938500/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4938500/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Biological age scores are an emerging tool to characterize aging by estimating chronological age based on physiological biomarkers. Various scores have shown associations with aging-related outcomes. This study assessed the relation between an age score based on brain MRI images (BrainAge) and an age score based on metabolomic biomarkers (MetaboAge). We trained a federated deep learning model to estimate BrainAge in three cohorts. The federated BrainAge model yielded significantly lower error for age prediction across the cohorts than locally trained models. Harmonizing the age interval between cohorts further improved BrainAge accuracy. Subsequently, we compared BrainAge with MetaboAge using federated association and survival analyses. The results showed a small association\r\nbetween BrainAge and MetaboAge as well as a higher predictive value for the time to mortality of both scores combined than for the individual scores. Hence, our study suggests that both aging scores capture different aspects of the aging process.","manuscriptTitle":"MRI-based and metabolomics-based age scores act synergetically for mortality prediction shown by multi-cohort federated learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-09-17 01:48:55","doi":"10.21203/rs.3.rs-4938500/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":"2788ff6a-9b33-4374-aea7-20bd3848da04","owner":[],"postedDate":"September 17th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":36801032,"name":"Health sciences/Medical research/Biomarkers/Predictive markers"},{"id":36801033,"name":"Biological sciences/Biotechnology/Metabolomics"},{"id":36801034,"name":"Health sciences/Health care/Medical imaging/Brain imaging"},{"id":36801035,"name":"Physical sciences/Mathematics and computing/Computer science"}],"tags":[],"updatedAt":"2024-09-17T01:48:57+00:00","versionOfRecord":[],"versionCreatedAt":"2024-09-17 01:48:55","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4938500","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4938500","identity":"rs-4938500","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}

Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy (via DOI) is the canonical version.

My notes (saved in your browser only)

Ask this paper AI returns verbatim quotes from the full text · source: preprint-html

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2024) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.

Source provenance

europepmc
last seen: 2026-05-20T01:45:00.602351+00:00
unpaywall
last seen: 2026-05-21T05:10:58.409756+00:00
License: CC-BY-4.0