Multi-Modal Federated Learning with Differential Privacy for Privacy-Preserving Healthcare AI

Multi-Modal Federated Learning with Differential Privacy for Privacy-Preserving Healthcare AI | 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 Multi-Modal Federated Learning with Differential Privacy for Privacy-Preserving Healthcare AI MdRokibul Hasan, Md Istiaq Ahmed, Sudip Saha, Tashnim Khan Ishika, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9108015/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 12 You are reading this latest preprint version Abstract The growing adoption of artificial intelligence in healthcare highlights the need for models that can leverage heterogeneous patient data while preserving strict privacy requirements. This paper proposes a novel multi-modal federated learning framework with differential privacy for decentralized healthcare AI. The model integrates electronic health records and ECG time-series using modality-specific encoders and a shared latent fusion network, enabling comprehensive representation learning without centralizing sensitive data. Differential privacy is incorporated into local updates to provide formal guarantees against information leakage in federated aggregation. Extensive experiments on real-world healthcare datasets show that the proposed method achieves $94.12%$ accuracy, $93.64%$ precision, $93.21%$ recall, $93.42%$ F1-score, and $95.03%$ AUC, outperforming centralized, single-modality, and non-private baselines. The framework also converges $32.4%$ faster than single-modality federated learning, reaching $90%$ accuracy in $35$ rounds. An ablation study confirms the contribution of multi-modal fusion and class balancing, while client variance analysis shows the lowest performance deviation ($\pm 1.2%$) under heterogeneous distributions. These results indicate that combining federated optimization, differential privacy, and multi-modal learning provides an effective and scalable solution for privacy-preserving clinical AI. Biological sciences/Computational biology and bioinformatics Physical sciences/Engineering Health sciences/Health care Physical sciences/Mathematics and computing Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 02 Apr, 2026 Reviews received at journal 21 Mar, 2026 Reviewers agreed at journal 19 Mar, 2026 Reviews received at journal 18 Mar, 2026 Reviewers agreed at journal 18 Mar, 2026 Reviewers agreed at journal 17 Mar, 2026 Reviewers agreed at journal 17 Mar, 2026 Reviewers invited by journal 17 Mar, 2026 Editor invited by journal 17 Mar, 2026 Editor assigned by journal 14 Mar, 2026 Submission checks completed at journal 14 Mar, 2026 First submitted to journal 12 Mar, 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-9108015","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":609028836,"identity":"7d006867-baf3-4b76-bc0a-e7b3bef1c4ab","order_by":0,"name":"MdRokibul Hasan","email":"","orcid":"","institution":"Southeast Missouri State University","correspondingAuthor":false,"prefix":"","firstName":"MdRokibul","middleName":"","lastName":"Hasan","suffix":""},{"id":609028837,"identity":"9afc386d-1baf-4236-bc9c-055a768a2f97","order_by":1,"name":"Md Istiaq Ahmed","email":"","orcid":"","institution":"Southeast Missouri State University","correspondingAuthor":false,"prefix":"","firstName":"Md","middleName":"Istiaq","lastName":"Ahmed","suffix":""},{"id":609028838,"identity":"b60ffa7d-0de2-4101-ad04-5c9f5b066734","order_by":2,"name":"Sudip Saha","email":"","orcid":"","institution":"Pace University","correspondingAuthor":false,"prefix":"","firstName":"Sudip","middleName":"","lastName":"Saha","suffix":""},{"id":609028839,"identity":"7f2fd388-a022-42c1-bc68-d859ac2a70c7","order_by":3,"name":"Tashnim Khan Ishika","email":"","orcid":"","institution":"Southeast Missouri State University","correspondingAuthor":false,"prefix":"","firstName":"Tashnim","middleName":"Khan","lastName":"Ishika","suffix":""},{"id":609028840,"identity":"8979fea0-3a39-4929-82e5-eaaf69103fd4","order_by":4,"name":"Hashibul Ahsan Shoaib","email":"","orcid":"","institution":"St. Francis College","correspondingAuthor":false,"prefix":"","firstName":"Hashibul","middleName":"Ahsan","lastName":"Shoaib","suffix":""},{"id":609028841,"identity":"8c7b2f96-8109-4ca0-9ba4-9dd71613ceb8","order_by":5,"name":"Md. Jakir Hossen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7klEQVRIiWNgGAWjYBACxgY2hgMMIAQCHyCUAfFaGGcQo4WBgQ1EQLQw8xCjhbn9WOLhCoY7cvL9h489ts3ZltjA3rxNgjHnMG6H9aQdOHiG4ZmxwY20dOPcbbcTG3iOlUkwbsOjpSG94WADw+HEDRI8ZtJgLRI5Zvi19D+HaJnff/6btCVIi/wbAlpmAB0G0tJwIIdNmhFsCw8hLc8SDjYYHAb5xUyyd9tt4zaetGKLxG3pOLUY9qcZf2yoOAwKsWcSP7fdlu1nP7zxxsdt1ri1NIBI5IgAx1MCQzNOLfK4JOpwahkFo2AUjIIRBwDHl1wN7KRR3AAAAABJRU5ErkJggg==","orcid":"","institution":"Multimedia University","correspondingAuthor":true,"prefix":"","firstName":"Md.","middleName":"Jakir","lastName":"Hossen","suffix":""}],"badges":[],"createdAt":"2026-03-12 19:53:32","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9108015/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9108015/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105563127,"identity":"52a5d193-703d-4823-9557-24912ac7edad","added_by":"auto","created_at":"2026-03-27 12:46:03","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1571722,"visible":true,"origin":"","legend":"","description":"","filename":"ScientificreportMultiModalFederatedLearningwithDifferential.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9108015/v1_covered_7505e3f5-8438-477c-aab7-4eb10b359009.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Multi-Modal Federated Learning with Differential Privacy for Privacy-Preserving Healthcare AI","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-9108015/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9108015/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The growing adoption of artificial intelligence in healthcare highlights the need for models that can leverage heterogeneous patient data while preserving strict privacy requirements. This paper proposes a novel multi-modal federated learning framework with differential privacy for decentralized healthcare AI. The model integrates electronic health records and ECG time-series using modality-specific encoders and a shared latent fusion network, enabling comprehensive representation learning without centralizing sensitive data. Differential privacy is incorporated into local updates to provide formal guarantees against information leakage in federated aggregation. Extensive experiments on real-world healthcare datasets show that the proposed method achieves $94.12\\%$ accuracy, $93.64\\%$ precision, $93.21\\%$ recall, $93.42\\%$ F1-score, and $95.03\\%$ AUC, outperforming centralized, single-modality, and non-private baselines. The framework also converges $32.4\\%$ faster than single-modality federated learning, reaching $90\\%$ accuracy in $35$ rounds. An ablation study confirms the contribution of multi-modal fusion and class balancing, while client variance analysis shows the lowest performance deviation ($\\pm 1.2\\%$) under heterogeneous distributions. These results indicate that combining federated optimization, differential privacy, and multi-modal learning provides an effective and scalable solution for privacy-preserving clinical AI.","manuscriptTitle":"Multi-Modal Federated Learning with Differential Privacy for Privacy-Preserving Healthcare AI","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-20 19:50:52","doi":"10.21203/rs.3.rs-9108015/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-04-02T06:22:39+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-21T23:36:09+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"35850779564641853065892962233730772914","date":"2026-03-19T16:28:46+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-18T21:06:41+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"268812935821431516634690473676370636802","date":"2026-03-18T17:18:00+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"24974027868505694648211907827007602405","date":"2026-03-17T23:19:25+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"6334847058437176489520864252565336317","date":"2026-03-17T16:57:50+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-03-17T15:33:00+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-03-17T12:32:11+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-03-14T13:38:15+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-14T13:37:28+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2026-03-12T19:51:44+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"81c4d7ce-63ec-4047-94b8-6573ad2da43e","owner":[],"postedDate":"March 20th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":64806439,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":64806440,"name":"Physical sciences/Engineering"},{"id":64806441,"name":"Health sciences/Health care"},{"id":64806442,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-04-29T19:54:08+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-20 19:50:52","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9108015","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9108015","identity":"rs-9108015","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}