NeighBERT: Medical Entity Linking Using Relation Induced Dense Retrieval

NeighBERT: Medical Entity Linking Using Relation Induced Dense Retrieval | 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 NeighBERT: Medical Entity Linking Using Relation Induced Dense Retrieval Ayush Singh, Saranya Krishnamoorthy, John Ortega This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-2050347/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 18 Jan, 2024 Read the published version in Journal of Healthcare Informatics Research → Version 1 posted 9 You are reading this latest preprint version Abstract One of the common tasks in clinical natural language processing is medical entity linking (MEL) which involves mention detection followed by linking the mention to an entity in a knowledge base. One reason that MEL has not been solved is due to a problem that occurs in language where ambiguous texts can be resolved to several named entities. This problem is exacerbated when processing text found in electronic health records. Recent work has shown that deep learning models based on transformers outperform previous methods on linking at higher rates of performance. We introduce NeighBERT, a custom pre-training technique which extends BERT \citep{devlin-etal-2019-bert} by encoding how entities are related within a knowledge graph. This technique adds relational context that has been traditionally missing in original BERT, helping resolve the ambiguity found in clinical text. In our experiments, NeighBERT improves the precision, recall and F1-score of the state of the art by 1--3 points for named entity recognition and 10--15 points for MEL on two widely known clinical datasets. Natural Language Processing Knowledge Graph Information Search and Retrieval Deep Learning Medical Entity Linking Biomedical Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 18 Jan, 2024 Read the published version in Journal of Healthcare Informatics Research → Version 1 posted Editorial decision: Major revision 19 Apr, 2023 Reviews received at journal 19 Apr, 2023 Reviews received at journal 11 Apr, 2023 Reviewers agreed at journal 09 Dec, 2022 Reviewers agreed at journal 17 Oct, 2022 Reviewers invited by journal 13 Oct, 2022 Editor assigned by journal 13 Sep, 2022 Submission checks completed at journal 13 Sep, 2022 First submitted to journal 09 Sep, 2022 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-2050347","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":136322297,"identity":"8fa8915d-6f44-4de1-a4fd-12ea6bc1791f","order_by":0,"name":"Ayush Singh","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA80lEQVRIiWNgGAWjYJACZiDmASLGBwwMEqRpYTYgSQtIFxtx6vln5Bh/LmCokzHnX3us4mObhTy/9OEDDD8qtuHUInEjx0x6BsNhHssZ79JuzmyTMJzZl5bA2HPmNm5rgFqYeRgO8BjcOGN2m+eMRILBGR4DZsY23FrkbwAdxsNQB9ZS/Aeshf8DXi0GN3IMpHkYmHkMzveYMTNUgG1hwKvF8MyzMmkeg8NAW3iMJXsqgH7pYTM4iM8vcseTN3/mqaizNzh/xvDDD4M6eX4e5ocPflTg8b5AAsh5QCyRgBA8gFs9EPAfQGeMglEwCkbBKEADAPDVTrG1qje3AAAAAElFTkSuQmCC","orcid":"","institution":"Evernorth Health Services","correspondingAuthor":true,"prefix":"","firstName":"Ayush","middleName":"","lastName":"Singh","suffix":""},{"id":136322298,"identity":"eced2880-1cf2-44fe-90cd-4f86a873db4d","order_by":1,"name":"Saranya Krishnamoorthy","email":"","orcid":"","institution":"Evernorth Health Services","correspondingAuthor":false,"prefix":"","firstName":"Saranya","middleName":"","lastName":"Krishnamoorthy","suffix":""},{"id":136322299,"identity":"442a3a96-d69e-4450-b924-9096a3f91893","order_by":2,"name":"John Ortega","email":"","orcid":"","institution":"Evernorth Health Services","correspondingAuthor":false,"prefix":"","firstName":"John","middleName":"","lastName":"Ortega","suffix":""}],"badges":[],"createdAt":"2022-09-09 22:14:09","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-2050347/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-2050347/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s41666-023-00136-3","type":"published","date":"2024-01-18T15:01:41+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":26530279,"identity":"0dd4d78b-71f0-4c53-b19f-4c2ae4217e53","added_by":"auto","created_at":"2022-09-15 21:49:27","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":899976,"visible":true,"origin":"","legend":"","description":"","filename":"JHIRSpringer2022NeighBERT2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-2050347/v1_covered.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"NeighBERT: Medical Entity Linking Using Relation Induced Dense Retrieval","fulltext":[{"header":"Full Text","content":"This preprint is available for \u003ca href='/article/rs-2050347/latest.pdf' target='_blank'\u003edownload as a PDF\u003c/a\u003e."}],"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":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"journal-of-healthcare-informatics-research","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jhir","sideBox":"Learn more about [Journal of Healthcare Informatics Research](http://link.springer.com/journal/41666)","snPcode":"41666","submissionUrl":"https://submission.nature.com/new-submission/41666/3","title":"Journal of Healthcare Informatics Research","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Natural Language Processing, Knowledge Graph, Information Search and Retrieval, Deep Learning, Medical Entity Linking, Biomedical","lastPublishedDoi":"10.21203/rs.3.rs-2050347/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-2050347/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"One of the common tasks in clinical natural language processing is medical entity linking (MEL) which involves mention detection followed by linking the mention to an entity in a knowledge base. One reason that MEL has not been solved is due to a problem that occurs in language where ambiguous texts can be resolved to several named entities. This problem is exacerbated when processing text found in electronic health records. Recent work has shown that deep learning models based on transformers outperform previous methods on linking at higher rates of performance. We introduce NeighBERT, a custom pre-training technique which extends BERT \\citep{devlin-etal-2019-bert} by encoding how entities are related within a knowledge graph. This technique adds relational context that has been traditionally missing in original BERT, helping resolve the ambiguity found in clinical text. In our experiments, NeighBERT improves the precision, recall and F1-score of the state of the art by 1--3 points for named entity recognition and 10--15 points for MEL on two widely known clinical datasets.","manuscriptTitle":"NeighBERT: Medical Entity Linking Using Relation Induced Dense Retrieval","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2022-09-15 21:49:18","doi":"10.21203/rs.3.rs-2050347/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Major revision","date":"2023-04-20T02:21:47+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2023-04-20T02:17:17+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2023-04-11T22:39:59+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"df6c0403-4da9-4f61-aa3f-aac95dd23bed","date":"2022-12-09T18:16:50+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"5d221e40-a870-41ca-910e-cb219517645f","date":"2022-10-17T17:03:56+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2022-10-14T02:48:11+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2022-09-13T11:39:43+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2022-09-13T11:39:40+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of Healthcare Informatics Research","date":"2022-09-09T22:02:49+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"journal-of-healthcare-informatics-research","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jhir","sideBox":"Learn more about [Journal of Healthcare Informatics Research](http://link.springer.com/journal/41666)","snPcode":"41666","submissionUrl":"https://submission.nature.com/new-submission/41666/3","title":"Journal of Healthcare Informatics Research","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"fc3cfdf6-e551-42fc-93be-3ee8cdab5e84","owner":[],"postedDate":"September 15th, 2022","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2024-01-22T15:07:28+00:00","versionOfRecord":{"articleIdentity":"rs-2050347","link":"https://doi.org/10.1007/s41666-023-00136-3","journal":{"identity":"journal-of-healthcare-informatics-research","isVorOnly":false,"title":"Journal of Healthcare Informatics Research"},"publishedOn":"2024-01-18 15:01:41","publishedOnDateReadable":"January 18th, 2024"},"versionCreatedAt":"2022-09-15 21:49:18","video":"","vorDoi":"10.1007/s41666-023-00136-3","vorDoiUrl":"https://doi.org/10.1007/s41666-023-00136-3","workflowStages":[]},"version":"v1","identity":"rs-2050347","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-2050347","identity":"rs-2050347","version":["v1"]},"buildId":"_2-kVJe1T_tPrBINL-cwx","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}