Data Encoding For Healthcare Data Democratisation and Information Leakage Prevention

Data Encoding For Healthcare Data Democratisation and Information Leakage Prevention | 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 Data Encoding For Healthcare Data Democratisation and Information Leakage Prevention Tingting Zhu, Jacob Armstrong, Vinayak Abrol, Yujiang Wang, David Clifton, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-2922432/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 21 Feb, 2024 Read the published version in Nature Communications → Version 1 posted You are reading this latest preprint version Abstract The lack of data democratization and information leakage from trained models hinder the development and acceptance of robust deep learning-based healthcare solutions. This paper argues that irreversible data encoding can provide an effective solution to achieve data democratization without violating the privacy constraints imposed on healthcare data and clinical models. An ideal encoding framework transforms the data into a new space where it is imperceptible to a manual or computational inspection. However, encoded data should preserve the semantics of the original data such that deep learning models can be trained effectively. This paper hypothesizes the characteristics of the desired encoding framework and then exploits random projections and random quantum encoding to realize this framework for dense and longitudinal or time-series data. Experimental evaluation highlights that models trained on encoded time-series data effectively uphold the information bottleneck principle and hence, exhibit lesser information leakage from trained models. Health sciences/Health care Health sciences/Medical research Full Text Additional Declarations There is NO Competing Interest. Supplementary Files RQESUP.pdf Cite Share Download PDF Status: Published Journal Publication published 21 Feb, 2024 Read the published version in Nature Communications → 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-2922432","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":203130370,"identity":"4e7143eb-84e4-455c-8cd0-78047c22822a","order_by":0,"name":"Tingting Zhu","email":"","orcid":"https://orcid.org/0000-0002-1552-5630","institution":"University of Oxford","correspondingAuthor":false,"prefix":"","firstName":"Tingting","middleName":"","lastName":"Zhu","suffix":""},{"id":203130371,"identity":"a1207cbc-54c4-4aee-9b6e-750c41622d13","order_by":1,"name":"Jacob Armstrong","email":"","orcid":"","institution":"University of Oxford","correspondingAuthor":false,"prefix":"","firstName":"Jacob","middleName":"","lastName":"Armstrong","suffix":""},{"id":203130372,"identity":"ff8f64ea-0efe-461a-bb7b-a61dd404e10f","order_by":2,"name":"Vinayak Abrol","email":"","orcid":"","institution":"IIIT Delhi","correspondingAuthor":false,"prefix":"","firstName":"Vinayak","middleName":"","lastName":"Abrol","suffix":""},{"id":203130373,"identity":"ec3642d0-0c78-4806-9c1a-e71a7e830218","order_by":3,"name":"Yujiang Wang","email":"","orcid":"","institution":"University of Oxford","correspondingAuthor":false,"prefix":"","firstName":"Yujiang","middleName":"","lastName":"Wang","suffix":""},{"id":203130374,"identity":"fd20ab02-28ea-46cf-a040-38b2950bcdd3","order_by":4,"name":"David Clifton","email":"","orcid":"","institution":"University of Oxford","correspondingAuthor":false,"prefix":"","firstName":"David","middleName":"","lastName":"Clifton","suffix":""},{"id":203130375,"identity":"aac320ae-d44b-421f-80bd-8b6b43dec1e9","order_by":5,"name":"Anshul Thakur","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABEElEQVRIiWNgGAWjYHACNgaGAgYGAxDNUIEswYNPiwGDBETLGZK1MLYRoYV/dvuzxzwGDHXm7MfSpCvn2eTJOzAfk2CosWMwOHMAqxaJO2fMjYFaJCx70o5Jnt2WVmx4gC3ZgOFYMoPB2Qbs1tzIYZMGaTE4kN4m2bjtcOLGBh7DBwxsBxgMzmPXIX8j/RlEy/nnQC1z/oO0GBxg+Idbi8GNBDOIlhtAhzU2HEiczwC0hbHtAE6HGd7IMZOcYyAhueHGs2TLhmPJiRuYgX5J7EvmkcThfTmgwyTeVNjwG5xPM7zZUGOXOL+9+ZjEh292cnxnErC7DAIkkJx6GEgk4ItIDCCP3QejYBSMglEwggEAp4VXcRpv0ywAAAAASUVORK5CYII=","orcid":"","institution":"University of Oxford","correspondingAuthor":true,"prefix":"","firstName":"Anshul","middleName":"","lastName":"Thakur","suffix":""}],"badges":[],"createdAt":"2023-05-11 19:39:38","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-2922432/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-2922432/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41467-024-45777-z","type":"published","date":"2024-02-21T05:00:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":51471522,"identity":"1edc9590-61d1-426e-b964-d376361d8753","added_by":"auto","created_at":"2024-02-22 08:07:11","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1241225,"visible":true,"origin":"","legend":"","description":"","filename":"RQEDatasharingandIBprinciple.pdf","url":"https://assets-eu.researchsquare.com/files/rs-2922432/v1_covered_05cd2e21-19f0-4cb9-981f-3e0d9148a9d4.pdf"},{"id":37411789,"identity":"2be321b5-2e6a-44fb-953b-60a26d551ba3","added_by":"auto","created_at":"2023-05-24 03:25:26","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":1048321,"visible":true,"origin":"","legend":"","description":"","filename":"RQESUP.pdf","url":"https://assets-eu.researchsquare.com/files/rs-2922432/v1/05cad9022118eb8826b4f65b.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Data Encoding For Healthcare Data Democratisation and Information Leakage Prevention","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-2922432/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-2922432/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The lack of data democratization and information leakage from trained models hinder the development and acceptance of robust deep learning-based healthcare solutions. This paper argues that irreversible data encoding can provide an effective solution to achieve data democratization without violating the privacy constraints imposed on healthcare data and clinical models. An ideal encoding framework transforms the data into a new space where it is imperceptible to a manual or computational inspection. However, encoded data should preserve the semantics of the original data such that deep learning models can be trained effectively. This paper hypothesizes the characteristics of the desired encoding framework and then exploits random projections and random quantum encoding to realize this framework for dense and longitudinal or time-series data. Experimental evaluation highlights that models trained on encoded time-series data effectively uphold the information bottleneck principle and hence, exhibit lesser information leakage from trained models.","manuscriptTitle":"Data Encoding For Healthcare Data Democratisation and Information Leakage Prevention","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2023-05-24 03:25:21","doi":"10.21203/rs.3.rs-2922432/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-communications","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"NCOMMS","sideBox":"Learn more about [Nature Communications](http://www.nature.com/ncomms/)","snPcode":"","submissionUrl":"https://mts-ncomms.nature.com/","title":"Nature Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Communications","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"e3a930a1-0b66-4c1f-90ce-5c8ef8b87053","owner":[],"postedDate":"May 24th, 2023","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":21757395,"name":"Health sciences/Health care"},{"id":21757396,"name":"Health sciences/Medical research"}],"tags":[],"updatedAt":"2024-02-22T08:06:56+00:00","versionOfRecord":{"articleIdentity":"rs-2922432","link":"https://doi.org/10.1038/s41467-024-45777-z","journal":{"identity":"nature-communications","isVorOnly":false,"title":"Nature Communications"},"publishedOn":"2024-02-21 05:00:00","publishedOnDateReadable":"February 21st, 2024"},"versionCreatedAt":"2023-05-24 03:25:21","video":"","vorDoi":"10.1038/s41467-024-45777-z","vorDoiUrl":"https://doi.org/10.1038/s41467-024-45777-z","workflowStages":[]},"version":"v1","identity":"rs-2922432","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-2922432","identity":"rs-2922432","version":["v1"]},"buildId":"J0_U0BvcaRcwD8yVFaRlm","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}