Establishing a Real-Time Biomarker-to-LLM Interface: A Modular Pipeline for HRV Signal Acquisition, Processing, and Physiological State Interpretation via Generative AI

Establishing a Real-Time Biomarker-to-LLM Interface: A Modular Pipeline for HRV Signal Acquisition, Processing, and Physiological State Interpretation via Generative AI | 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 Short Report Establishing a Real-Time Biomarker-to-LLM Interface: A Modular Pipeline for HRV Signal Acquisition, Processing, and Physiological State Interpretation via Generative AI Morris Gellisch, Boris Burr This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7091387/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Large language models can summarize research, generate clinical reasoning, and carry on convincing conversations. But for all their linguistic power, they rely entirely on what we tell them — subjective reports, delayed inputs, and filtered impressions. If we want them to become true partners in learning, decision-making, or care, they need something more: biosignals, not just words. Therefore, we present a streamlined architecture for routing real-time heart rate variability (HRV) data from a wearable sensor directly into a generative AI environment. Using a validated HRV sensor, we decoded Bluetooth-transmitted R-R intervals via a custom Python script and derived core HRV metrics (HR, RMSSD, SDNN, LF/HF ratio, pNN50) in real time. These values were published via REST and WebSocket endpoints through a FastAPI backend, making them continuously accessible to external applications — including OpenAI’s GPT models. The result: a live data pipeline from autonomic input to conversational output. A language model that doesn’t just talk back, but responds to real-time physiological shifts in natural language. In multiple proof-of-concept scenarios, ChatGPT accessed real-time HRV data, performed descriptive analyses, generated visualizations, and adapted its feedback in response to autonomic shifts induced by low and high cognitive load. This system marks an early prototype for bioadaptive AI — where your body becomes part of the prompt. Biological sciences/Computational biology and bioinformatics Physical sciences/Engineering Physical sciences/Mathematics and computing Embodied AI 1 Physiologically Coupled Language Models 2 Real-Time HRV-AI Integration 3 Biofeedback-Enhanced LLM Interaction 4 OpenAI Applications in Digital Health 5. Stress Detection via AI Affective Computing Full Text Additional Declarations No competing interests reported. Supplementary Files Supplement1LMMPrompts.docx Cite Share Download PDF Status: Posted Version 1 posted 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-7091387","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Short Report","associatedPublications":[],"authors":[{"id":483815675,"identity":"4e16b80a-aeaf-444d-9e2f-83a77ac82670","order_by":0,"name":"Morris Gellisch","email":"data:image/png;base64,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","orcid":"","institution":"Ruhr-University Bochum","correspondingAuthor":true,"prefix":"","firstName":"Morris","middleName":"","lastName":"Gellisch","suffix":""},{"id":483815677,"identity":"93d064de-839a-4dc2-b33b-e0fddcad5a91","order_by":1,"name":"Boris Burr","email":"","orcid":"","institution":"Ruhr-University Bochum","correspondingAuthor":false,"prefix":"","firstName":"Boris","middleName":"","lastName":"Burr","suffix":""}],"badges":[],"createdAt":"2025-07-10 09:38:09","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7091387/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7091387/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":87174065,"identity":"343b0cae-a330-4559-a63e-e731e4150622","added_by":"auto","created_at":"2025-07-21 08:09:15","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":648361,"visible":true,"origin":"","legend":"","description":"","filename":"PhysinAIMANUSCRPTMGBBnpjDM.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7091387/v1_covered_fe374154-98d6-4f5e-9890-2b4601a0d95a.pdf"},{"id":86743419,"identity":"cfd22f85-4496-4d3d-af63-d418c8a0eb6d","added_by":"auto","created_at":"2025-07-15 07:22:15","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":18937,"visible":true,"origin":"","legend":"","description":"","filename":"Supplement1LMMPrompts.docx","url":"https://assets-eu.researchsquare.com/files/rs-7091387/v1/4af5dfc2e3da84539e7e8146.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Establishing a Real-Time Biomarker-to-LLM Interface: A Modular Pipeline for HRV Signal Acquisition, Processing, and Physiological State Interpretation via Generative AI","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"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":"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},"keywords":"Embodied AI 1, Physiologically Coupled Language Models 2, Real-Time HRV-AI Integration 3, Biofeedback-Enhanced LLM Interaction 4, OpenAI Applications in Digital Health 5. Stress Detection via AI, Affective Computing","lastPublishedDoi":"10.21203/rs.3.rs-7091387/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7091387/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eLarge language models can summarize research, generate clinical reasoning, and carry on convincing conversations. But for all their linguistic power, they rely entirely on what we tell them \u0026mdash; subjective reports, delayed inputs, and filtered impressions. If we want them to become true partners in learning, decision-making, or care, they need something more: biosignals, not just words.\u003c/p\u003e\u003cp\u003eTherefore, we present a streamlined architecture for routing real-time heart rate variability (HRV) data from a wearable sensor directly into a generative AI environment. Using a validated HRV sensor, we decoded Bluetooth-transmitted R-R intervals via a custom Python script and derived core HRV metrics (HR, RMSSD, SDNN, LF/HF ratio, pNN50) in real time. These values were published via REST and WebSocket endpoints through a FastAPI backend, making them continuously accessible to external applications \u0026mdash; including OpenAI\u0026rsquo;s GPT models.\u003c/p\u003e\u003cp\u003eThe result: a live data pipeline from autonomic input to conversational output. A language model that doesn\u0026rsquo;t just talk back, but responds to real-time physiological shifts in natural language. In multiple proof-of-concept scenarios, ChatGPT accessed real-time HRV data, performed descriptive analyses, generated visualizations, and adapted its feedback in response to autonomic shifts induced by low and high cognitive load. This system marks an early prototype for bioadaptive AI \u0026mdash; where your body becomes part of the prompt.\u003c/p\u003e","manuscriptTitle":"Establishing a Real-Time Biomarker-to-LLM Interface: A Modular Pipeline for HRV Signal Acquisition, Processing, and Physiological State Interpretation via Generative AI","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-07-15 07:14:10","doi":"10.21203/rs.3.rs-7091387/v1","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}}],"origin":"","ownerIdentity":"d8bc6aa8-4649-4d53-89a1-811bf83eb4c3","owner":[],"postedDate":"July 15th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":51371749,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":51371750,"name":"Physical sciences/Engineering"},{"id":51371751,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2025-07-21T08:08:55+00:00","versionOfRecord":[],"versionCreatedAt":"2025-07-15 07:14:10","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7091387","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7091387","identity":"rs-7091387","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}