A Framework for Extraction of Clinical Information from Radiological Mammography Reports Using Large Language Models and Retrieval Augmented Generation.

A Framework for Extraction of Clinical Information from Radiological Mammography Reports Using Large Language Models and Retrieval Augmented 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 Research Article A Framework for Extraction of Clinical Information from Radiological Mammography Reports Using Large Language Models and Retrieval Augmented Generation. Eduardo Godoy, Joaquín de Ferrari, Sofia Lazo, Catalina Pancheco, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4927320/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 4 You are reading this latest preprint version Abstract Background: The application of text mining in radiological reports is crucial for many tasks but principally analyzing and projecting trends to enhance diagnostic accuracy. This is especially important in mammography reports, where early detection is crucial. Large language models (LLMs) provide a viable alternative. They can generate accurate results from a limited set of examples compared with the traditional state-of-the-art models. Methods: This work presents a framework utilizing a general proposed retrieval-augmented generation (RAG) and large language model LLM to create a replicable model capable of structuring mammography radiology reports and extracting relevant concepts associated with the findings. The resulting model is applied to a real-world scenario, using a dataset of mammography radiology reports provided by a hospital. These reports, written by radiologists, are in free text and Spanish. The application of the designed framework is evaluated across several LLMs, and its results are compared to a conventional and specialized NER-type model based on BERT, using a dataset labeled by radiologists. Results: Several models have been implemented and evaluated with the proposed LLM framework. In Named Entity Recognition (NER) tasks using GPT-4, the zero-shot learning scenario achieved an F1-score of 0.80, while the five-shot scenario reached an F1-score of 0.96. This is comparable to the specific-context NER-BERT model, which achieved an F1-score of 0.97. Similarly, in Relation Extraction tasks, we achieved an F1-score of 0.93, a task for which a specialized model was not available. Conclusion: The results demonstrate that large language models (LLMs) can benefit from additional in-prompt examples and achieve results comparable to those of specialized models like NER-BERT. Additionally, this study shows that through a well-defined framework, it is possible to effectively leverage the capabilities of LLMs for specific purposes such as NER and Relation Extraction over clinical text and mammography reports. Breast Cancer Mammoghraphy Reports Natural Language Processing - NLP Large Language Model - LLM NER Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 27 Aug, 2024 Editor assigned by journal 27 Aug, 2024 Submission checks completed at journal 27 Aug, 2024 First submitted to journal 16 Aug, 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-4927320","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":345760950,"identity":"1d07b1a1-39f2-47d9-9457-16dfedf0097b","order_by":0,"name":"Eduardo Godoy","email":"data:image/png;base64,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","orcid":"","institution":"University of Valparaíso","correspondingAuthor":true,"prefix":"","firstName":"Eduardo","middleName":"","lastName":"Godoy","suffix":""},{"id":345760951,"identity":"f12857e5-249c-4017-93a4-ef4fec2f93fb","order_by":1,"name":"Joaquín de Ferrari","email":"","orcid":"","institution":"Federico Santa María Technical University","correspondingAuthor":false,"prefix":"","firstName":"Joaquín","middleName":"","lastName":"de Ferrari","suffix":""},{"id":345760952,"identity":"274e7d02-9d48-4d9e-8119-ae3371e517dd","order_by":2,"name":"Sofia Lazo","email":"","orcid":"","institution":"University of Valparaíso","correspondingAuthor":false,"prefix":"","firstName":"Sofia","middleName":"","lastName":"Lazo","suffix":""},{"id":345760953,"identity":"61cf8e9b-5a2c-4fe3-89c0-b95506624a6b","order_by":3,"name":"Catalina Pancheco","email":"","orcid":"","institution":"University of Valparaíso","correspondingAuthor":false,"prefix":"","firstName":"Catalina","middleName":"","lastName":"Pancheco","suffix":""},{"id":345760954,"identity":"3c0f7539-2ed8-4dd0-9f1f-16f9ef809b32","order_by":4,"name":"Diego Mellado","email":"","orcid":"","institution":"University of Valparaíso","correspondingAuthor":false,"prefix":"","firstName":"Diego","middleName":"","lastName":"Mellado","suffix":""},{"id":345760955,"identity":"4070593c-ba67-4a8d-b29b-31cbbf4e4ae7","order_by":5,"name":"Alex Saez","email":"","orcid":"","institution":"Interclinica","correspondingAuthor":false,"prefix":"","firstName":"Alex","middleName":"","lastName":"Saez","suffix":""},{"id":345760956,"identity":"1124e38c-f310-46c2-b71f-ee4faa7cb0a1","order_by":6,"name":"Steren Chabert","email":"","orcid":"","institution":"University of Valparaíso","correspondingAuthor":false,"prefix":"","firstName":"Steren","middleName":"","lastName":"Chabert","suffix":""},{"id":345760957,"identity":"cbe5518a-7fad-466f-a134-6cce7eee2ce2","order_by":7,"name":"Rodrigo Salas","email":"","orcid":"","institution":"University of Valparaíso","correspondingAuthor":false,"prefix":"","firstName":"Rodrigo","middleName":"","lastName":"Salas","suffix":""}],"badges":[],"createdAt":"2024-08-17 00:41:34","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4927320/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4927320/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":65316214,"identity":"9c364502-a618-43d6-b117-d987f07f6510","added_by":"auto","created_at":"2024-09-26 03:37:49","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":672805,"visible":true,"origin":"","legend":"","description":"","filename":"BMC2023TemplateLLMMammographyv1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4927320/v1_covered_22a33618-5c1c-4177-8754-ca7358575cec.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Framework for Extraction of Clinical Information from Radiological Mammography Reports Using Large Language Models and Retrieval Augmented Generation.","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":"bmc-medical-informatics-and-decision-making","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"midm","sideBox":"Learn more about [BMC Medical Informatics and Decision Making](http://bmcmedinformdecismak.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/midm/default.aspx","title":"BMC Medical Informatics and Decision Making","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Breast Cancer, Mammoghraphy Reports, Natural Language Processing - NLP, Large Language Model - LLM, NER","lastPublishedDoi":"10.21203/rs.3.rs-4927320/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4927320/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eBackground: The application of text mining in radiological reports is crucial for many tasks but principally analyzing and projecting trends to enhance diagnostic accuracy. This is especially important in mammography reports, where early detection is crucial. Large language models (LLMs) provide a viable alternative. They can generate accurate results from a limited set of examples compared with the traditional state-of-the-art models.\u0026nbsp;\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eMethods: This work presents a framework utilizing a general proposed retrieval-augmented generation (RAG) and large language model LLM to create a replicable model capable of structuring mammography radiology reports and extracting relevant concepts associated with the findings. The resulting model is applied to a real-world scenario, using a dataset of mammography radiology reports provided by a hospital. These reports, written by radiologists, are in free text and Spanish. The application of the designed framework is evaluated across several LLMs, and its results are compared to a conventional and specialized NER-type model based on BERT, using a dataset labeled by radiologists.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eResults: \u0026nbsp;Several models have been implemented and evaluated with the proposed LLM framework. In Named Entity Recognition (NER) tasks using GPT-4, the zero-shot learning scenario achieved an F1-score of 0.80, while the five-shot scenario reached an F1-score of 0.96. This is comparable to the specific-context NER-BERT model, which achieved an F1-score of 0.97. Similarly, in Relation Extraction tasks, we achieved an F1-score of 0.93, a task for which a specialized model was not available.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eConclusion: The results demonstrate that large language models (LLMs) can benefit from additional in-prompt examples and achieve results comparable to those of specialized models like NER-BERT. Additionally, this study shows that through a well-defined framework, it is possible to effectively leverage the capabilities of LLMs for specific purposes such as NER and Relation Extraction over clinical text and mammography reports.\u003c/p\u003e","manuscriptTitle":"A Framework for Extraction of Clinical Information from Radiological Mammography Reports Using Large Language Models and Retrieval Augmented Generation.","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-09-26 03:29:41","doi":"10.21203/rs.3.rs-4927320/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-08-27T12:40:20+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-08-27T11:51:50+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-08-27T10:36:11+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Medical Informatics and Decision Making","date":"2024-08-17T00:40:11+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-medical-informatics-and-decision-making","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"midm","sideBox":"Learn more about [BMC Medical Informatics and Decision Making](http://bmcmedinformdecismak.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/midm/default.aspx","title":"BMC Medical Informatics and Decision Making","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"b4486d04-5d72-4b16-bc38-381877c9e389","owner":[],"postedDate":"September 26th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-22T04:24:22+00:00","versionOfRecord":[],"versionCreatedAt":"2024-09-26 03:29:41","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4927320","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4927320","identity":"rs-4927320","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}