Interoperable web platform based on large language models for medicals data analysis

Interoperable web platform based on large language models for medicals data analysis | 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 Interoperable web platform based on large language models for medicals data analysis Marcello Carvalho dos Reis, Rafaelly Rios dos Santos, Md Rafiul Hassan, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5815389/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 12 You are reading this latest preprint version Abstract This paper introduces an interoperable web platform for managing medical data, prioritizing security, and integration of information from multiple sources using FHIR (Fast Healthcare Interoperability Resources). The objective is to optimize medical record analysis with artificial intelligence (AI) and machine learning, offering automatic alerts and preventive recommendations while complying with the General Data Protection Law (GDPL in English; LGPD in Portuguese). The platform facilitates efficient sharing of data among hospitals, clinics, remote devices, and healthcare systems, improving diagnostic and treatment accuracy. The methodology involved creating a secure, LGPD-compliant web platform, the integration of data through FHIR to ensure interoperability. AI algorithms analyze medical data, generate alerts, and provide personalized recommendations. Performance was assessed in controlled and stress tests, focusing on scalability and security. Results highlighted promising performance of the Retrieve Augmentation Generation (RAG) technique with BAAI/bge-small-en embedding models. Metrics such as BertF1, BertP, and BertR ranged from 0.389 to 0.538, averaging 0.43, indicating moderate consistency. The average Bleu score was 0.442, reflecting diverse response quality, while Rouge metrics averaged 0.326, indicating lowerprecision. Performance with Chest X-rays and MedQA datasets showed better results with Chest X-rays, achieving higher scores but higher perplexity (3.635e4), indicating challenges in generating clinical text. MedQA showed greater response diversity (0.807) but lower precision. In qualitative analysis, Chest X- rays demonstrated higher semantic similarity (mean 0.767) compared to MedQA (mean 0.754). During load testing, the platform remained stable as user numbers increased, but response times grew under stress, suggesting bottlenecks in high-demand scenarios. In conclusion, the platform is a promising tool for integrating medical data and supporting clinical decisions. The FHIR standard ensured interoperability, while AI effectively analyzed records and issued alerts. Adjustments are needed in response times under heavy loads and improvements in infrastructure and mobile experience to encourage greater patient adoption. Health sciences/Health care Health sciences/Health care/Health care economics Health sciences/Health care/Health policy Full Text Additional Declarations No competing interests reported. Supplementary Files 1TemplateforsubmissionstoScientificReportsVersoFinal21.zip Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 14 Apr, 2025 Reviews received at journal 12 Apr, 2025 Reviewers agreed at journal 07 Apr, 2025 Reviewers agreed at journal 07 Apr, 2025 Reviews received at journal 07 Apr, 2025 Reviews received at journal 02 Apr, 2025 Reviewers agreed at journal 02 Apr, 2025 Reviewers agreed at journal 02 Apr, 2025 Reviewers agreed at journal 02 Apr, 2025 Reviewers invited by journal 02 Apr, 2025 Submission checks completed at journal 27 Mar, 2025 First submitted to journal 26 Mar, 2025 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-5815389","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":437334237,"identity":"d8974387-7857-4817-815b-eeb6312c3747","order_by":0,"name":"Marcello Carvalho dos Reis","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA5klEQVRIiWNgGAWjYNCCAgsgwdjA8IEBzHgAYhMABhJgLYwzGEAMZgNitQDV8hCjRbf97MMPHwwk5Mzbm5s/29RIJDZIJDN+YNxxD6cWszPpxpIzDCSMZc4cbJPOOQbWwizBeKYYt5YDaWzMPAYSiTMkEtuYc9hAWvKPMTC2JeDWcv4ZG/MfkBb5h82fLf6BbWHDr+UG0BYGsC2MDdKMbURpecYs2QP0iwRPYptkb5+EcRvPY2aJxDP4HJbG+OFHhY2cBPvxxx9+fLOR7WcHhtjHHbi1YAI2EEGKhlEwCkbBKBgFmAAAxE5KUzHKwKcAAAAASUVORK5CYII=","orcid":"","institution":"Universidade Federal do Ceará","correspondingAuthor":true,"prefix":"","firstName":"Marcello","middleName":"Carvalho dos","lastName":"Reis","suffix":""},{"id":437334238,"identity":"497aef45-62fe-46d4-87a4-6e71401c6e9f","order_by":1,"name":"Rafaelly Rios dos Santos","email":"","orcid":"","institution":"Universidade Federal do Ceará","correspondingAuthor":false,"prefix":"","firstName":"Rafaelly","middleName":"Rios dos","lastName":"Santos","suffix":""},{"id":437334239,"identity":"942cf5b1-c649-4eea-8b6f-2adef472586e","order_by":2,"name":"Md Rafiul Hassan","email":"","orcid":"","institution":"Central Connecticut State University","correspondingAuthor":false,"prefix":"","firstName":"Md","middleName":"Rafiul","lastName":"Hassan","suffix":""},{"id":437334240,"identity":"1899d453-adbb-48fb-9f03-44c348b4cda3","order_by":3,"name":"Mohammad Mehedi Hassan","email":"","orcid":"","institution":"King Saud University","correspondingAuthor":false,"prefix":"","firstName":"Mohammad","middleName":"Mehedi","lastName":"Hassan","suffix":""},{"id":437334241,"identity":"f72f6b76-d43b-4bd4-86ea-620c9ff894e2","order_by":4,"name":"Daniel Santos da Silva","email":"","orcid":"","institution":"Universidade Federal do Ceará","correspondingAuthor":false,"prefix":"","firstName":"Daniel","middleName":"Santos da","lastName":"Silva","suffix":""},{"id":437334242,"identity":"c633d557-9b7e-435f-bcb9-cd2fc3068e48","order_by":5,"name":"Pedro Lino Azevedo Landim","email":"","orcid":"","institution":"Universidade Federal do Ceará","correspondingAuthor":false,"prefix":"","firstName":"Pedro","middleName":"Lino Azevedo","lastName":"Landim","suffix":""},{"id":437334243,"identity":"8c9bf3e3-51b5-4fda-9b73-62daa3c1c451","order_by":6,"name":"Victor Hugo Costa de Albuquerque","email":"","orcid":"","institution":"Universidade Federal do Ceará","correspondingAuthor":false,"prefix":"","firstName":"Victor","middleName":"Hugo Costa de","lastName":"Albuquerque","suffix":""}],"badges":[],"createdAt":"2025-01-12 20:53:05","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5815389/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5815389/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":79851723,"identity":"0ea29a63-5320-4a76-84c6-f673c319d945","added_by":"auto","created_at":"2025-04-03 14:51:05","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1708926,"visible":true,"origin":"","legend":"","description":"","filename":"OFICIALV2TemplateforsubmissionstoScientificReportsVersoFinal1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5815389/v1_covered_77f4859c-31c7-407e-9d04-3c3b2a5494d8.pdf"},{"id":79851469,"identity":"56362c3a-ef2e-4708-ab48-f5e19f635bd6","added_by":"auto","created_at":"2025-04-03 14:43:02","extension":"zip","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":3844094,"visible":true,"origin":"","legend":"","description":"","filename":"1TemplateforsubmissionstoScientificReportsVersoFinal21.zip","url":"https://assets-eu.researchsquare.com/files/rs-5815389/v1/23c2cc58ed459eeafb2912e2.zip"}],"financialInterests":"No competing interests reported.","formattedTitle":"Interoperable web platform based on large language models for medicals data analysis","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":"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-5815389/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5815389/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"This paper introduces an interoperable web platform for managing medical data, prioritizing security, and integration of information from multiple sources using FHIR (Fast Healthcare Interoperability Resources). The objective is to optimize medical record analysis with artificial intelligence (AI) and machine learning, offering automatic alerts and preventive recommendations while complying with the General Data Protection Law (GDPL in English; LGPD in Portuguese). The platform facilitates efficient sharing of data among hospitals, clinics, remote devices, and healthcare systems, improving diagnostic and treatment accuracy. The methodology involved creating a secure, LGPD-compliant web platform, the integration of data through FHIR to ensure interoperability. AI algorithms analyze medical data, generate alerts, and provide personalized recommendations. Performance was assessed in controlled and stress tests, focusing on scalability and security. Results highlighted promising performance of the Retrieve Augmentation Generation (RAG) technique with BAAI/bge-small-en embedding models. Metrics such as BertF1, BertP, and BertR ranged from 0.389 to 0.538, averaging 0.43, indicating moderate consistency. The average Bleu score was 0.442, reflecting diverse response quality, while Rouge metrics averaged 0.326, indicating lowerprecision. Performance with Chest X-rays and MedQA datasets showed better results with Chest X-rays, achieving higher scores but higher perplexity (3.635e4), indicating challenges in generating clinical text. MedQA showed greater response diversity (0.807) but lower precision. In qualitative analysis, Chest X- rays demonstrated higher semantic similarity (mean 0.767) compared to MedQA (mean 0.754). During load testing, the platform remained stable as user numbers increased, but response times grew under stress, suggesting bottlenecks in high-demand scenarios. In conclusion, the platform is a promising tool for integrating medical data and supporting clinical decisions. The FHIR standard ensured interoperability, while AI effectively analyzed records and issued alerts. Adjustments are needed in response times under heavy loads and improvements in infrastructure and mobile experience to encourage greater patient adoption.","manuscriptTitle":"Interoperable web platform based on large language models for medicals data analysis","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-03 14:42:57","doi":"10.21203/rs.3.rs-5815389/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-04-14T08:47:15+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-04-12T04:46:25+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"118096603712485326964523290487141076196","date":"2025-04-08T02:39:35+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"34968524882550421529118186177785177857","date":"2025-04-07T22:41:51+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-04-07T07:16:02+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-04-02T09:24:06+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"267496887396402182137062516203580736949","date":"2025-04-02T06:19:04+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"319978182819577914104996924000655632964","date":"2025-04-02T05:45:30+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"201654236664472209120281031224413888403","date":"2025-04-02T04:41:46+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-04-02T04:40:43+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-03-27T09:39:44+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-03-26T10:40:26+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":"5380487d-5c82-4a7f-b87a-f28058d1d7ae","owner":[],"postedDate":"April 3rd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":46566022,"name":"Health sciences/Health care"},{"id":46566023,"name":"Health sciences/Health care/Health care economics"},{"id":46566024,"name":"Health sciences/Health care/Health policy"}],"tags":[],"updatedAt":"2025-04-18T06:38:13+00:00","versionOfRecord":[],"versionCreatedAt":"2025-04-03 14:42:57","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5815389","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5815389","identity":"rs-5815389","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}