Medical HyperRAG: A Hypergraph-Enhanced Retrieval-Augmented Generation Framework for Clinical Question Answering

Medical HyperRAG: A Hypergraph-Enhanced Retrieval-Augmented Generation Framework for Clinical Question Answering | 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 Medical HyperRAG: A Hypergraph-Enhanced Retrieval-Augmented Generation Framework for Clinical Question Answering Fangfang Xu, Yifan Kuai, Chao Gao, Dan Luo, Jinguang Gu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8497459/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 10 You are reading this latest preprint version Abstract Clinical question answering plays a crucial role in intelligent healthcare, where reliable reasoning over patient-specific conditions and up-to-date medical evidence is essential for clinical decision support. However, large language models often suffer from hallucinations, outdated internal knowledge, and weak interpretability when facing multi-entity and multi-condition reasoning tasks. To address these limitations, this paper proposes Medical HyperRAG, a hypergraph-enhanced Retrieval-Augmented Generation framework that unifies structured and unstructured medical knowledge into a patient-centered reasoning paradigm. Specifically, heterogeneous information from electronic health records, clinical cases, and medical guidelines is organized through a ClinBridge HyperGraph, in which hyperedges capture high-order relations among symptoms, tests, diagnoses, and treatments. This design preserves logical constraints and temporal dependencies inherent to real clinical workflows. During inference, the framework performs structure-aware retrieval and context construction by verbalizing hyperedges into natural-language representations, enabling the LLM to generate answers grounded in both individualized and guideline-based knowledge. Experiments on real-world clinical datasets demonstrate that Medical HyperRAG substantially improves diagnostic and treatment accuracy compared with existing RAG baselines, achieving notable gains in factual precision, coherence, and semantic relevance. Ablation studies further confirm that the fusion of personalized case data and authoritative guidelines, along with phased retrieval and natural-language hyperedge representation, provides complementary benefits for reasoning interpretability and robustness. Overall, Medical HyperRAG establishes a unified, interpretable pathway for integrating high-order medical knowledge into large language models, thereby advancing trustworthy AI-assisted clinical question answering and decision support. Biological sciences/Computational biology and bioinformatics Health sciences/Health care Physical sciences/Mathematics and computing Health sciences/Medical research Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 10 May, 2026 Reviews received at journal 30 Apr, 2026 Reviewers agreed at journal 24 Apr, 2026 Reviewers agreed at journal 19 Apr, 2026 Reviewers agreed at journal 19 Apr, 2026 Reviewers invited by journal 19 Apr, 2026 Editor assigned by journal 13 Apr, 2026 Editor invited by journal 03 Feb, 2026 Submission checks completed at journal 30 Jan, 2026 First submitted to journal 30 Jan, 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-8497459","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":629100431,"identity":"69620328-4a83-4f4c-8838-a45a55e2e5f5","order_by":0,"name":"Fangfang Xu","email":"","orcid":"","institution":"Wuhan University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Fangfang","middleName":"","lastName":"Xu","suffix":""},{"id":629100435,"identity":"e79d4c50-0f17-4554-a98b-c0d898f66339","order_by":1,"name":"Yifan Kuai","email":"","orcid":"","institution":"Wuhan University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Yifan","middleName":"","lastName":"Kuai","suffix":""},{"id":629100439,"identity":"23dd62da-7bb5-46b0-bcd5-878757b52ff7","order_by":2,"name":"Chao Gao","email":"","orcid":"","institution":"Wuhan University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Chao","middleName":"","lastName":"Gao","suffix":""},{"id":629100443,"identity":"894ebf40-c61d-4c39-99bd-9596af0690bc","order_by":3,"name":"Dan Luo","email":"","orcid":"","institution":"Lehigh University","correspondingAuthor":false,"prefix":"","firstName":"Dan","middleName":"","lastName":"Luo","suffix":""},{"id":629100446,"identity":"30177f17-f741-4fda-8438-aa59c90ae171","order_by":4,"name":"Jinguang Gu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA+UlEQVRIiWNgGAWjYDACZhBRgcQGAx6CWs5AFEG0sBHSAgKMbaRokW/nTnxcOM8mz569x/BxAcPhxPnzGxgfvG1jkDfHocXgMO9m45nb0op5eM4YG88AatlwjIHZcG4bg+HOBhxamHm3SfNuO5zYI5G7TZqH4XbiBjYGNmneNoYEgwM4HNYM0jIHrGX7b5CW+W0M7L/xaWE4DNLSALGFGaSl4RgDGzM+LWC/8BxLS+w5c/6z9AyD/8YbjiU2S845J2G4AZfD+s9ufMxTY5PY3t6W+LmgIk12fvPhgx/elNnI43QYmqUggrEBSEgQpX4UjIJRMApGAXYAAPFSVKkxXo7kAAAAAElFTkSuQmCC","orcid":"","institution":"Wuhan University of Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Jinguang","middleName":"","lastName":"Gu","suffix":""}],"badges":[],"createdAt":"2026-01-02 00:53:06","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8497459/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8497459/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108181323,"identity":"0821016a-f165-42d8-bcb4-b4f28f9c29b5","added_by":"auto","created_at":"2026-04-30 08:58:33","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":497915,"visible":true,"origin":"","legend":"","description":"","filename":"MedicalHyperRAG.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8497459/v1_covered_8e29de7d-ae18-4582-a66a-3c46f650c756.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Medical HyperRAG: A Hypergraph-Enhanced Retrieval-Augmented Generation Framework for Clinical Question Answering","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"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-8497459/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8497459/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Clinical question answering plays a crucial role in intelligent healthcare, where reliable reasoning over patient-specific conditions and up-to-date medical evidence is essential for clinical decision support. However, large language models often suffer from hallucinations, outdated internal knowledge, and weak interpretability when facing multi-entity and multi-condition reasoning tasks. To address these limitations, this paper proposes Medical HyperRAG, a hypergraph-enhanced Retrieval-Augmented Generation framework that unifies structured and unstructured medical knowledge into a patient-centered reasoning paradigm. Specifically, heterogeneous information from electronic health records, clinical cases, and medical guidelines is organized through a ClinBridge HyperGraph, in which hyperedges capture high-order relations among symptoms, tests, diagnoses, and treatments. This design preserves logical constraints and temporal dependencies inherent to real clinical workflows. During inference, the framework performs structure-aware retrieval and context construction by verbalizing hyperedges into natural-language representations, enabling the LLM to generate answers grounded in both individualized and guideline-based knowledge. Experiments on real-world clinical datasets demonstrate that Medical HyperRAG substantially improves diagnostic and treatment accuracy compared with existing RAG baselines, achieving notable gains in factual precision, coherence, and semantic relevance. Ablation studies further confirm that the fusion of personalized case data and authoritative guidelines, along with phased retrieval and natural-language hyperedge representation, provides complementary benefits for reasoning interpretability and robustness. Overall, Medical HyperRAG establishes a unified, interpretable pathway for integrating high-order medical knowledge into large language models, thereby advancing trustworthy AI-assisted clinical question answering and decision support.","manuscriptTitle":"Medical HyperRAG: A Hypergraph-Enhanced Retrieval-Augmented Generation Framework for Clinical Question Answering","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-27 08:29:57","doi":"10.21203/rs.3.rs-8497459/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-05-10T23:59:45+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-30T11:54:31+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"324869264806742874792027981097278601608","date":"2026-04-24T15:09:37+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"7089747276217457118878054650980354417","date":"2026-04-19T14:28:04+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"153397388701058879542869253938573329425","date":"2026-04-19T13:40:46+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-19T13:20:14+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-13T15:10:06+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-02-03T12:10:15+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-01-30T13:45:09+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2026-01-30T13:12:15+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":"143a2027-898b-4be1-b855-b0882f829abd","owner":[],"postedDate":"April 27th, 2026","published":true,"recentEditorialEvents":[{"type":"editorInvitedReview","content":"","date":"2026-05-10T23:59:45+00:00","index":92,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-30T11:54:31+00:00","index":91,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":66963969,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":66963970,"name":"Health sciences/Health care"},{"id":66963971,"name":"Physical sciences/Mathematics and computing"},{"id":66963972,"name":"Health sciences/Medical research"}],"tags":[],"updatedAt":"2026-04-27T08:29:57+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-27 08:29:57","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8497459","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8497459","identity":"rs-8497459","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}