Knowledge-Graph-Enabled Biomedical Entity Linking: A Survey

Knowledge-Graph-Enabled Biomedical Entity Linking: A Survey | 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 Research Article Knowledge-Graph-Enabled Biomedical Entity Linking: A Survey Jiyun Shi, Zhimeng Yuan, Wenxuan Guo, Chen Ma, Jiehao Chen, Meihui Zhang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-2183349/v2 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 02 May, 2023 Read the published version in World Wide Web → Version 2 posted 7 You are reading this latest preprint version Show more versions Abstract Biomedical Entity Linking (BM-EL) task, which aims to match biomedical mentions in articles to entities in a certain knowledge base (e.g., the Unified Medical Language System), draws dramatic attention in recent years. BM-EL can help to disambiguate medical terms and link to rich semantic information in the biomedical knowledge base, which can act as an essential means for many downstream applications.Although entity linking tasks have been investigated in the general domain and achieved great success, many challenges remain in the biomedical field, for instance, highly complex terminology, less training data, and entity ambiguity.In this survey, we categorize BM-EL methods into rule-based, machine learning, and deep learning models according to the development of the model paradigm and provide a comprehensive review of each approach.In-depth study of current BM-EL efforts, we group the model architectures into four categories: joint entity recognition and linking, graph-based global entity disambiguation, cross-lingual architectures, and model-efficiency improvement.We further introduce six well-established datasets that are commonly used for BM-EL tasks. Furthermore, we present a comparison of the different methods and discuss their advantages and disadvantages.Finally, we discuss the limitations of existing methods for BM-EL and discuss promising future research directions. Biomedical Entity Linking Biomedical Entity Disambiguation Knowledge Base Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 02 May, 2023 Read the published version in World Wide Web → Version 2 posted Editorial decision: Major revision 16 Dec, 2022 Reviews received at journal 06 Nov, 2022 Reviewers agreed at journal 03 Nov, 2022 Reviewers invited by journal 03 Nov, 2022 Editor assigned by journal 01 Nov, 2022 Submission checks completed at journal 26 Oct, 2022 First submitted to journal 25 Oct, 2022 You are reading this latest preprint version Show more versions 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-2183349","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[{"code":1,"date":"2022-10-24 18:42:53","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}}],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":158599884,"identity":"151e99ff-f2fd-4d48-88a0-7b132bcac0ba","order_by":0,"name":"Jiyun Shi","email":"","orcid":"","institution":"Beijing Institute of Technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Jiyun","middleName":"","lastName":"Shi","suffix":""},{"id":158599885,"identity":"9344f147-5b2d-4e1c-8e51-a736b3cdded4","order_by":1,"name":"Zhimeng Yuan","email":"","orcid":"","institution":"Beijing Institute of Technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Zhimeng","middleName":"","lastName":"Yuan","suffix":""},{"id":158599886,"identity":"8b602e1c-94fe-402f-ac9e-521266b344f8","order_by":2,"name":"Wenxuan Guo","email":"","orcid":"","institution":"Beijing Institute of Technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Wenxuan","middleName":"","lastName":"Guo","suffix":""},{"id":158599887,"identity":"1c394472-b693-4b45-9dd4-80071691e4cd","order_by":3,"name":"Chen Ma","email":"","orcid":"","institution":"City University of Hong Kong","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Chen","middleName":"","lastName":"Ma","suffix":""},{"id":158599888,"identity":"4bf8be1f-24d2-4226-96d9-b477c7347039","order_by":4,"name":"Jiehao Chen","email":"","orcid":"","institution":"China Academy of Industrial Internet","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Jiehao","middleName":"","lastName":"Chen","suffix":""},{"id":158599889,"identity":"2be83516-7731-4047-a2cc-739967b3aeaf","order_by":5,"name":"Meihui Zhang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA+0lEQVRIiWNgGAWjYFACxjYGBgMwYmD42CABogyI18I4s0FCgggtDGwMMJOZeRsYCGvRbW9ue8xTwGBvzn728GvbHRZ1DOzN2yQYau7g1GJ25mC7MY8BA7NlT16ade4ZoMN4jpVJMBx7hlvLjcQ2aaAWNoMDOWbGuW1ALRI5ZhKMDYdxa7n/EKyFx+D8GzNjS5AW+TcEtNxgBGuRMLiRY/yYEWwLDwEtZxLbJOcYMBgY3Hhjxth7RkKyjSet2CLhGB4tx48/k3jzh8He4HyO8YefO+r4+dkPb7zxoQa3Fij4DyLYwFEPjqYEQhqggPkDkQpHwSgYBaNghAEA0E5LiWznYwEAAAAASUVORK5CYII=","orcid":"","institution":"Beijing Institute of Technology","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Meihui","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2022-10-19 14:14:31","currentVersionCode":2,"declarations":"","doi":"10.21203/rs.3.rs-2183349/v2","doiUrl":"https://doi.org/10.21203/rs.3.rs-2183349/v2","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s11280-023-01144-4","type":"published","date":"2023-05-02T20:44:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":44728299,"identity":"129dd232-2510-416c-9504-c49c98d56764","added_by":"auto","created_at":"2023-10-16 21:02:26","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1459474,"visible":true,"origin":"","legend":"","description":"","filename":"KnowledgeGraphEnabledBiomedicalEntityLinkingASurvey.pdf","url":"https://assets-eu.researchsquare.com/files/rs-2183349/v2_covered_255d2a53-71bc-4ec5-9ffe-336f7cdc8d90.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Knowledge-Graph-Enabled Biomedical Entity Linking: A Survey","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":"world-wide-web","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"wwwj","sideBox":"Learn more about [World Wide Web](http://link.springer.com/journal/11280)","snPcode":"11280","submissionUrl":"https://submission.nature.com/new-submission/11280/3","title":"World Wide Web","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Biomedical Entity Linking, Biomedical Entity Disambiguation, Knowledge Base","lastPublishedDoi":"10.21203/rs.3.rs-2183349/v2","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-2183349/v2","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Biomedical Entity Linking (BM-EL) task, which aims to match biomedical mentions in articles to entities in a certain knowledge base (e.g., the Unified Medical Language System), draws dramatic attention in recent years. BM-EL can help to disambiguate medical terms and link to rich semantic information in the biomedical knowledge base, which can act as an essential means for many downstream applications.Although entity linking tasks have been investigated in the general domain and achieved great success, many challenges remain in the biomedical field, for instance, highly complex terminology, less training data, and entity ambiguity.In this survey, we categorize BM-EL methods into rule-based, machine learning, and deep learning models according to the development of the model paradigm and provide a comprehensive review of each approach.In-depth study of current BM-EL efforts, we group the model architectures into four categories: joint entity recognition and linking, graph-based global entity disambiguation, cross-lingual architectures, and model-efficiency improvement.We further introduce six well-established datasets that are commonly used for BM-EL tasks. Furthermore, we present a comparison of the different methods and discuss their advantages and disadvantages.Finally, we discuss the limitations of existing methods for BM-EL and discuss promising future research directions.","manuscriptTitle":"Knowledge-Graph-Enabled Biomedical Entity Linking: A Survey","msid":"","msnumber":"","nonDraftVersions":[{"code":"","date":"2022-12-30 11:44:14","doi":"","editorialEvents":[{"type":"decision","content":"Accepted","date":"2023-01-20T02:15:52+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2023-01-09T03:14:40+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"66b75fe2-07c0-4c12-a06d-f5347f639dc5","date":"2023-01-09T01:58:17+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2023-01-08T14:48:53+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2023-01-02T18:46:24+00:00","index":"","fulltext":""},{"type":"submitted","content":"World Wide Web","date":"2022-12-30T11:39:14+00:00","index":"","fulltext":""}],"status":"private","journal":{"display":true,"email":"[email protected]","identity":"world-wide-web","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"wwwj","sideBox":"Learn more about [World Wide Web](http://link.springer.com/journal/11280)","snPcode":"11280","submissionUrl":"https://submission.nature.com/new-submission/11280/3","title":"World Wide Web","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}},{"code":2,"date":"2022-12-09 19:11:33","doi":"10.21203/rs.3.rs-2183349/v2","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Major revision","date":"2022-12-16T13:58:31+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2022-11-07T01:52:37+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"059ef7e1-5218-4934-87ba-8912567c600c","date":"2022-11-03T20:20:59+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2022-11-03T14:09:15+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2022-11-02T02:31:22+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2022-10-26T18:48:42+00:00","index":"","fulltext":""},{"type":"submitted","content":"World Wide Web","date":"2022-10-26T01:36:17+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"world-wide-web","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"wwwj","sideBox":"Learn more about [World Wide Web](http://link.springer.com/journal/11280)","snPcode":"11280","submissionUrl":"https://submission.nature.com/new-submission/11280/3","title":"World Wide Web","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"03acaf45-9615-4d4c-a54d-d6cf953e462f","owner":[],"postedDate":"December 9th, 2022","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2023-10-16T20:52:45+00:00","versionOfRecord":{"articleIdentity":"rs-2183349","link":"https://doi.org/10.1007/s11280-023-01144-4","journal":{"identity":"world-wide-web","isVorOnly":false,"title":"World Wide Web"},"publishedOn":"2023-05-02 20:44:00","publishedOnDateReadable":"May 2nd, 2023"},"versionCreatedAt":"2022-12-09 19:11:33","video":"","vorDoi":"10.1007/s11280-023-01144-4","vorDoiUrl":"https://doi.org/10.1007/s11280-023-01144-4","workflowStages":[]},"version":"v2","identity":"rs-2183349","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-2183349","identity":"rs-2183349","version":["v2"]},"buildId":"FbvkV6FR0MCFSLy54lSbu","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}