A Retrieval Augmented System for Cardiological Electronic Health Records.

A Retrieval Augmented System for Cardiological Electronic Health Records. | 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 Retrieval Augmented System for Cardiological Electronic Health Records. Annamaria Defilippo, Giovanni Canino, Nicola Procopio, Albino Trapuzzano, and 5 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8436294/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 24 Mar, 2026 Read the published version in Discover Artificial Intelligence → Version 1 posted 10 You are reading this latest preprint version Abstract Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) systems have significantly advanced data modelling capabilities and improved opportunities for extracting knowledge from vast and heterogeneous biomedical datasets. Recent research has increasingly focused on integrating LLMs with custom-designed RAGs to create systems capable of handling complex biomedical challenges, with a growing demand for more reliable and precise prediction mechanisms in health-related contexts. This study introduces CardioTRAP, an architecture specifically designed to manage biomedical data, with a primary focus on cardiology. The system employs advanced indexing techniques to enable efficient storage and retrieval by integrating deep learning models that generate contextual and clinically relevant insights. By adopting a hybrid approach that combines supervised and unsupervised learning methods, CardioTRAP ensures both high accuracy and scalability, supporting predictive analytics, patient risk stratification, and the discovery of novel biomarkers. Benchmarks and practical applications, evaluated through state-of-the-art metrics, underscore its ability to enhance the identification of critical clinical features. Finally, CardioTRAP demonstrates how the integration of data management and RAG systems can serve as a bridge between biomedical research and clinical practice. Large Language Models Retrieval-Augmented Generation systems Electronic Health Records Clinical Data Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 24 Mar, 2026 Read the published version in Discover Artificial Intelligence → Version 1 posted Editorial decision: Revision requested 04 Feb, 2026 Reviews received at journal 28 Jan, 2026 Reviewers agreed at journal 28 Jan, 2026 Reviews received at journal 26 Jan, 2026 Reviewers agreed at journal 14 Jan, 2026 Reviewers invited by journal 07 Jan, 2026 Editor invited by journal 07 Jan, 2026 Editor assigned by journal 04 Jan, 2026 Submission checks completed at journal 02 Jan, 2026 First submitted to journal 02 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-8436294","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":571120342,"identity":"398c3467-25a9-4566-a8e3-314b95143c02","order_by":0,"name":"Annamaria Defilippo","email":"","orcid":"","institution":"Magna Graecia University","correspondingAuthor":false,"prefix":"","firstName":"Annamaria","middleName":"","lastName":"Defilippo","suffix":""},{"id":571120346,"identity":"a5081778-c41b-4e93-968c-48bccafb3a90","order_by":1,"name":"Giovanni Canino","email":"","orcid":"","institution":"Magna Graecia University","correspondingAuthor":false,"prefix":"","firstName":"Giovanni","middleName":"","lastName":"Canino","suffix":""},{"id":571120347,"identity":"92e708e3-a3a6-4082-860b-a53a1412b9f9","order_by":2,"name":"Nicola Procopio","email":"","orcid":"","institution":"AC software","correspondingAuthor":false,"prefix":"","firstName":"Nicola","middleName":"","lastName":"Procopio","suffix":""},{"id":571120350,"identity":"82e477da-988c-4ff7-aa09-52a1fea6f9f7","order_by":3,"name":"Albino Trapuzzano","email":"","orcid":"","institution":"Magna Graecia University","correspondingAuthor":false,"prefix":"","firstName":"Albino","middleName":"","lastName":"Trapuzzano","suffix":""},{"id":571120351,"identity":"23b1f662-b9e7-4707-b73a-2c5f61e720ce","order_by":4,"name":"Sabato Sorrentino","email":"","orcid":"","institution":"Magna Graecia University","correspondingAuthor":false,"prefix":"","firstName":"Sabato","middleName":"","lastName":"Sorrentino","suffix":""},{"id":571120354,"identity":"8e3c5ec5-ccea-41ed-af58-e44cb7b44c28","order_by":5,"name":"ciro Indolfi","email":"","orcid":"","institution":"University of Calabria","correspondingAuthor":false,"prefix":"","firstName":"ciro","middleName":"","lastName":"Indolfi","suffix":""},{"id":571120357,"identity":"4026a4db-f14e-4238-a489-2e39d9e9610c","order_by":6,"name":"Patrizia Vizza","email":"","orcid":"","institution":"Magna Graecia University","correspondingAuthor":false,"prefix":"","firstName":"Patrizia","middleName":"","lastName":"Vizza","suffix":""},{"id":571120358,"identity":"d51d4055-b950-4729-837b-354c2278a5f7","order_by":7,"name":"Pierangelo Veltri","email":"","orcid":"","institution":"University of Calabria","correspondingAuthor":false,"prefix":"","firstName":"Pierangelo","middleName":"","lastName":"Veltri","suffix":""},{"id":571120360,"identity":"52767a61-743a-4158-8fd7-b570e0ea5964","order_by":8,"name":"Pietro Hiram Guzzi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAArklEQVRIiWNgGAWjYBACAwhpw8DAjOASpSUNpoUIPVAlh9H4+IA5/xrjjz8KziduZ2d+/IGh4A9hLZYz3hgYSBjcTtzZzAZ0FVEOu3HGIMEAqGXDYR6GBKK1HEgwOAfWcoA4Led7DBsOGBwAaWFsINIWtmLGBoNk4w2H2YwZEgyMibHl8OaPP/7YyW44f/jxhw9/5AhrYZBIQOIk4FCECvgPEKVsFIyCUTAKRjIAALx3OC2pERg3AAAAAElFTkSuQmCC","orcid":"","institution":"Magna Graecia University","correspondingAuthor":true,"prefix":"","firstName":"Pietro","middleName":"Hiram","lastName":"Guzzi","suffix":""}],"badges":[],"createdAt":"2025-12-23 17:53:23","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8436294/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8436294/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s44163-026-01128-z","type":"published","date":"2026-03-24T16:12:27+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":99912568,"identity":"8ab16650-1e4e-49c7-937f-0b41beba0680","added_by":"auto","created_at":"2026-01-09 18:39:26","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":9400,"visible":true,"origin":"","legend":"","description":"","filename":"aebf73d361ed4be6aa202f6c9ab74da8.json","url":"https://assets-eu.researchsquare.com/files/rs-8436294/v1/f17e99e37a7f626b80d87ae4.json"},{"id":105755305,"identity":"7033d4b8-3f42-4e9e-996b-88b0c6e545de","added_by":"auto","created_at":"2026-03-30 16:26:39","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":935687,"visible":true,"origin":"","legend":"","description":"","filename":"Archivio.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8436294/v1_covered_1024bd01-4209-4cb2-a752-48fa5f03dfaa.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Retrieval Augmented System for Cardiological Electronic Health Records.","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":"discover-artificial-intelligence","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"diai","sideBox":"Learn more about [Discover Artificial Intelligence](https://www.springer.com/44163)","snPcode":"","submissionUrl":"","title":"Discover Artificial Intelligence","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Discover Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Large Language Models, Retrieval-Augmented Generation systems, Electronic Health Records, Clinical Data","lastPublishedDoi":"10.21203/rs.3.rs-8436294/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8436294/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) systems have significantly advanced data modelling capabilities and improved opportunities for extracting knowledge from vast and heterogeneous biomedical datasets. Recent research has increasingly focused on integrating LLMs with custom-designed RAGs to create systems capable of handling complex biomedical challenges, with a growing demand for more reliable and precise prediction mechanisms in health-related contexts. This study introduces CardioTRAP, an architecture specifically designed to manage biomedical data, with a primary focus on cardiology. The system employs advanced indexing techniques to enable efficient storage and retrieval by integrating deep learning models that generate contextual and clinically relevant insights. By adopting a hybrid approach that combines supervised and unsupervised learning methods, CardioTRAP ensures both high accuracy and scalability, supporting predictive analytics, patient risk stratification, and the discovery of novel biomarkers. Benchmarks and practical applications, evaluated through state-of-the-art metrics, underscore its ability to enhance the identification of critical clinical features. Finally, CardioTRAP demonstrates how the integration of data management and RAG systems can serve as a bridge between biomedical research and clinical practice.","manuscriptTitle":"A Retrieval Augmented System for Cardiological Electronic Health Records.","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-09 18:39:22","doi":"10.21203/rs.3.rs-8436294/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-02-04T11:30:02+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-01-28T12:35:35+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"271255040326122080311679772507216897759","date":"2026-01-28T06:23:15+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-01-26T07:54:13+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"128973140419644036177731005928736320356","date":"2026-01-15T00:46:54+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-01-07T08:07:30+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-01-07T07:20:11+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-01-04T13:49:50+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-01-02T16:26:30+00:00","index":"","fulltext":""},{"type":"submitted","content":"Discover Artificial Intelligence","date":"2026-01-02T16:24:25+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"discover-artificial-intelligence","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"diai","sideBox":"Learn more about [Discover Artificial Intelligence](https://www.springer.com/44163)","snPcode":"","submissionUrl":"","title":"Discover Artificial Intelligence","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Discover Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"2594211c-9410-4672-91fc-7316d4906973","owner":[],"postedDate":"January 9th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-03-30T16:23:40+00:00","versionOfRecord":{"articleIdentity":"rs-8436294","link":"https://doi.org/10.1007/s44163-026-01128-z","journal":{"identity":"discover-artificial-intelligence","isVorOnly":false,"title":"Discover Artificial Intelligence"},"publishedOn":"2026-03-24 16:12:27","publishedOnDateReadable":"March 24th, 2026"},"versionCreatedAt":"2026-01-09 18:39:22","video":"","vorDoi":"10.1007/s44163-026-01128-z","vorDoiUrl":"https://doi.org/10.1007/s44163-026-01128-z","workflowStages":[]},"version":"v1","identity":"rs-8436294","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8436294","identity":"rs-8436294","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}