Preserving Information while Respecting Privacy: An Information Theoretic Framework for Synthetic Health Data Generation

Preserving Information while Respecting Privacy: An Information Theoretic Framework for Synthetic Health Data Generation | 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 Preserving Information while Respecting Privacy: An Information Theoretic Framework for Synthetic Health Data Generation Nadir Sella, Florent Guinot, Nikita Lagrange, Laurent-Philippe Albou, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3908503/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 23 Jan, 2025 Read the published version in npj Digital Medicine → Version 1 posted 11 You are reading this latest preprint version Abstract Generating synthetic data from medical records is a complex task intensified by patient privacy concerns. In recent years, multiple approaches have been reported for the generation of synthetic data, however, limited attention was given to jointly evaluate the quality and the privacy of the generated data. The quality and privacy of synthetic data stem from multivariate associations across variables, which cannot be assessed by comparing univariate distributions with the original data. Here, we introduce a novel algorithm (MIIC-SDG) for generating synthetic data from electronic records based on a multivariate information framework and Bayesian network theory. We also propose a new metric to quantitatively assess the trade-off between the quality and privacy of synthetic data generation methods. The performance of MIIC-SDG is demonstrated on two clinical datasets and favorably compares with state-of-the-art synthetic data generation methods, based on the trade-off between several quality and privacy metrics. Biological sciences/Cancer/Breast cancer Biological sciences/Computational biology and bioinformatics/Computational models Biological sciences/Computational biology and bioinformatics/Statistical methods Biological sciences/Computational biology and bioinformatics/Machine learning Full Text Additional Declarations (Not answered) Cite Share Download PDF Status: Published Journal Publication published 23 Jan, 2025 Read the published version in npj Digital Medicine → Version 1 posted Editorial decision: revise 01 Apr, 2024 Review # 3 received at journal 30 Mar, 2024 Review # 2 received at journal 22 Mar, 2024 Reviewer # 3 agreed at journal 14 Mar, 2024 Review # 1 received at journal 12 Mar, 2024 Reviewer # 2 agreed at journal 06 Mar, 2024 Reviewer # 1 agreed at journal 04 Mar, 2024 Reviewers invited by journal 16 Feb, 2024 Editor assigned by journal 29 Jan, 2024 Submission checks completed at journal 29 Jan, 2024 First submitted to journal 29 Jan, 2024 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-3908503","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":273214817,"identity":"1b840c4b-5f57-4db0-b72a-7789eb60f1f5","order_by":0,"name":"Nadir Sella","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3UlEQVRIiWNgGAWjYHACgwNAQoaPgRlES8gQrYWHjYEtAaSFhygtDBAtPBAGQfXm7Ic3Hq74Y8PDxn7m86sbNRY8DOyHj27Ap8WyJ63g4Nm2NB42ntxt1jnHgA7jSUu7gd8jOQYHGxsOAx2Wu804hw2oRYLHDL+W828MDjb8+c/Dxv/mmXHOP2K03ADa0sB2gIdNIof5cW4bUVqeFRxsbEsGanlmxpzbJwH0FCG/nE/e/LHhj50cP3/y48853+rk+NkPH8OrBRmwSYBJYpWDAPMHUlSPglEwCkbByAEA0U1F0/bke/4AAAAASUVORK5CYII=","orcid":"","institution":"Institut Roche","correspondingAuthor":true,"prefix":"","firstName":"Nadir","middleName":"","lastName":"Sella","suffix":""},{"id":273214818,"identity":"f4c30907-1946-4f82-b609-9cd9ae289303","order_by":1,"name":"Florent Guinot","email":"","orcid":"","institution":"Institut Roche","correspondingAuthor":false,"prefix":"","firstName":"Florent","middleName":"","lastName":"Guinot","suffix":""},{"id":273214819,"identity":"3008e0a1-85ba-49dc-aaea-06a06811dd74","order_by":2,"name":"Nikita Lagrange","email":"","orcid":"","institution":"Institut Curie","correspondingAuthor":false,"prefix":"","firstName":"Nikita","middleName":"","lastName":"Lagrange","suffix":""},{"id":273214820,"identity":"9f439633-cc20-49d3-a135-762af26f3372","order_by":3,"name":"Laurent-Philippe Albou","email":"","orcid":"https://orcid.org/0000-0001-5801-1974","institution":"Institut Roche","correspondingAuthor":false,"prefix":"","firstName":"Laurent-Philippe","middleName":"","lastName":"Albou","suffix":""},{"id":273214821,"identity":"bbd19886-4416-4575-b359-8488fb1afe77","order_by":4,"name":"Jonathan Desponds","email":"","orcid":"https://orcid.org/0000-0001-7112-3217","institution":"Institut Roche","correspondingAuthor":false,"prefix":"","firstName":"Jonathan","middleName":"","lastName":"Desponds","suffix":""},{"id":273214822,"identity":"1475ebaf-8315-425e-b65e-84e5ad64584b","order_by":5,"name":"Herve Isambert","email":"","orcid":"","institution":"Institut Curie","correspondingAuthor":false,"prefix":"","firstName":"Herve","middleName":"","lastName":"Isambert","suffix":""}],"badges":[],"createdAt":"2024-01-29 08:50:40","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3908503/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3908503/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41746-025-01431-6","type":"published","date":"2025-01-23T05:00:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":74533779,"identity":"dbd4c4a4-3b17-476a-8427-8b5c7d524734","added_by":"auto","created_at":"2025-01-23 08:09:25","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2319065,"visible":true,"origin":"","legend":"","description":"","filename":"ArticlePreservingInformationwhileRespectingPrivacy.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3908503/v1_covered_d5ed32c7-448f-4387-b6c0-5601c7a7f9e6.pdf"}],"financialInterests":"(Not answered)","formattedTitle":"Preserving Information while Respecting Privacy: An Information Theoretic Framework for Synthetic Health Data Generation","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":"npj-digital-medicine","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"npjdigitalmed","sideBox":"Learn more about [npj Digital Medicine](http://www.nature.com/npjdigitalmed/)","snPcode":"41746","submissionUrl":"https://submission.springernature.com/new-submission/41746/3","title":"npj Digital Medicine","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-3908503/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3908503/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Generating synthetic data from medical records is a complex task intensified by patient privacy concerns. In recent years, multiple approaches have been reported for the generation of synthetic data, however, limited attention was given to jointly evaluate the quality and the privacy of the generated data. The quality and privacy of synthetic data stem from multivariate associations across variables, which cannot be assessed by comparing univariate distributions with the original data. Here, we introduce a novel algorithm (MIIC-SDG) for generating synthetic data from electronic records based on a multivariate information framework and Bayesian network theory. We also propose a new metric to quantitatively assess the trade-off between the quality and privacy of synthetic data generation methods. The performance of MIIC-SDG is demonstrated on two clinical datasets and favorably compares with state-of-the-art synthetic data generation methods, based on the trade-off between several quality and privacy metrics.","manuscriptTitle":"Preserving Information while Respecting Privacy: An Information Theoretic Framework for Synthetic Health Data Generation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-02-19 06:42:45","doi":"10.21203/rs.3.rs-3908503/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"revise","date":"2024-04-01T05:03:56+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"This content is not available.","date":"2024-03-30T21:18:32+00:00","index":3,"fulltext":"This content is not available."},{"type":"editorInvitedReview","content":"This content is not available.","date":"2024-03-22T13:09:45+00:00","index":2,"fulltext":"This content is not available."},{"type":"reviewerAgreed","content":"This content is not available.","date":"2024-03-14T05:15:33+00:00","index":3,"fulltext":"This content is not available."},{"type":"editorInvitedReview","content":"This content is not available.","date":"2024-03-12T16:14:43+00:00","index":1,"fulltext":"This content is not available."},{"type":"reviewerAgreed","content":"This content is not available.","date":"2024-03-06T14:54:00+00:00","index":2,"fulltext":"This content is not available."},{"type":"reviewerAgreed","content":"This content is not available.","date":"2024-03-04T18:57:14+00:00","index":1,"fulltext":"This content is not available."},{"type":"reviewersInvited","content":"","date":"2024-02-16T13:24:05+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-01-29T09:59:06+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-01-29T09:55:43+00:00","index":"","fulltext":""},{"type":"submitted","content":"npj Digital Medicine","date":"2024-01-29T08:46:41+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"npj-digital-medicine","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"npjdigitalmed","sideBox":"Learn more about [npj Digital Medicine](http://www.nature.com/npjdigitalmed/)","snPcode":"41746","submissionUrl":"https://submission.springernature.com/new-submission/41746/3","title":"npj Digital Medicine","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"d4eb0620-42b0-4135-8a16-49d83a11f60b","owner":[],"postedDate":"February 19th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":28802151,"name":"Biological sciences/Cancer/Breast cancer"},{"id":28802152,"name":"Biological sciences/Computational biology and bioinformatics/Computational models"},{"id":28802153,"name":"Biological sciences/Computational biology and bioinformatics/Statistical methods"},{"id":28802154,"name":"Biological sciences/Computational biology and bioinformatics/Machine learning"}],"tags":[],"updatedAt":"2025-01-23T08:09:07+00:00","versionOfRecord":{"articleIdentity":"rs-3908503","link":"https://doi.org/10.1038/s41746-025-01431-6","journal":{"identity":"npj-digital-medicine","isVorOnly":false,"title":"npj Digital Medicine"},"publishedOn":"2025-01-23 05:00:00","publishedOnDateReadable":"January 23rd, 2025"},"versionCreatedAt":"2024-02-19 06:42:45","video":"","vorDoi":"10.1038/s41746-025-01431-6","vorDoiUrl":"https://doi.org/10.1038/s41746-025-01431-6","workflowStages":[]},"version":"v1","identity":"rs-3908503","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3908503","identity":"rs-3908503","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}