Privacy-PreservingLLM Middleware in LIS: Edge-Computing for Coagulation InterpretationUnder High-Dimensional Noise

Privacy-PreservingLLM Middleware in LIS: Edge-Computing for Coagulation InterpretationUnder High-Dimensional Noise | 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 Privacy-PreservingLLM Middleware in LIS: Edge-Computing for Coagulation InterpretationUnder High-Dimensional Noise Zihao Zhou This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9171815/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 Background: The integration of clinical decision support into primary careLaboratory Information Systems (LIS) is severely hindered by strictprivacy regulations and limited computing infrastructure. We propose aprivacy-preserving, edge-computing Large Language Model (LLM)middleware to interpret pre-analytical coagulation tests, addressingthe clinical constraints of data compliance, hardware poverty, andzero-tolerance for AI hallucinations. Methods: We developed a local Retrieval-Augmented Generation (RAG) architectureusing a 4-bit quantized Qwen2.5-7B model deployed via the Ollamaframework on a commercial 32\,GB RAM terminal without a dedicated GPU.To rigorously validate the system, we generated a 2{,}000-casesynthetic baseline of APTT tests and injected 30% semantic and 15%lexical noise to simulate real-world LIS inputs. Output safety wasstrictly enforced utilising Pydantic V2 schemas and a Tenacity-drivenself-reflection mechanism (maximum 3 retries). Results: The proposed LLM-RAG middleware demonstrated exceptional robustness,maintaining a Guideline Concordance Accuracy (\((ACC_{gc})\)) of 97.00%under high-dimensional noise, whereas the traditional rule-basedbaseline collapsed to 10.00%. The system successfully constrainedhallucinations, recording a Critical Violation Rate (CVR) of only1.50%. Clinical and hardware viability were proven with a throughputof 1.45\,RPS and an average latency of 1.38\,seconds (strictly belowthe 3.0\,s threshold), while achieving a Cohen's Kappa score of 0.88in an independent AI-as-Expert adjudication protocol. Conclusion: This edge-deployed LLM paradigm provides a highly reliable,zero-marginal-cost alternative for LIS modernisation, enabling secureand robust AI integration in resource-constrained medical environments. Large Language Model Edge Computing Laboratory InformationSystem Coagulation Tests Clinical Decision Support ArtificialIntelligence Full Text Additional Declarations No competing interests reported. Supplementary Files ESM1.pdf 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-9171815","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":609155445,"identity":"6606d306-a744-46c0-815a-3b4d76aa144d","order_by":0,"name":"Zihao Zhou","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAyUlEQVRIiWNgGAWjYDACCSD+gMRnbCBGC+MMBgMStTDzkKSFf3bzMWmbP38SG9gPb93Mw2Aju+EA87MHeC25cyxNOrfNILGBJ63sNg9DmvGGA2zmBvi0GEjkmN3ObQBqkeAxA2o5nLjhAA+bBEEtFn/gWv4TqYWBDa7lAGEtEjfS0n/2thkbtwH9cnOOQbLxzMNsZni18M9IPmzw44+cbD/74W033lTYyfYdb36GVwscsDGAIgcUVMxEqYcAvEE7CkbBKBgFIxgAALLbQ+MzECSdAAAAAElFTkSuQmCC","orcid":"","institution":"Chongqing Medical University","correspondingAuthor":true,"prefix":"","firstName":"Zihao","middleName":"","lastName":"Zhou","suffix":""}],"badges":[],"createdAt":"2026-03-19 16:53:52","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9171815/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9171815/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105163865,"identity":"34c5acf8-370c-494b-ade6-a9c1e8b155ec","added_by":"auto","created_at":"2026-03-23 00:54:27","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":495454,"visible":true,"origin":"","legend":"","description":"","filename":"Article.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9171815/v1_covered_7b45852d-5da1-4757-8f49-c0eb3e93473a.pdf"},{"id":105163864,"identity":"19a0c565-e968-47f0-8bff-f8836f632cca","added_by":"auto","created_at":"2026-03-23 00:54:22","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":175256,"visible":true,"origin":"","legend":"","description":"","filename":"ESM1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9171815/v1/2662eb5ec145205d5f82b7d3.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Privacy-PreservingLLM Middleware in LIS: Edge-Computing for Coagulation InterpretationUnder High-Dimensional Noise","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"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":"Large Language Model, Edge Computing, Laboratory InformationSystem, Coagulation Tests, Clinical Decision Support, ArtificialIntelligence","lastPublishedDoi":"10.21203/rs.3.rs-9171815/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9171815/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003e\u003cstrong\u003eBackground:\u003c/strong\u003eThe integration of clinical decision support into primary careLaboratory Information Systems (LIS) is severely hindered by strictprivacy regulations and limited computing infrastructure. We propose aprivacy-preserving, edge-computing Large Language Model (LLM)middleware to interpret pre-analytical coagulation tests, addressingthe clinical constraints of data compliance, hardware poverty, andzero-tolerance for AI hallucinations.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eMethods:\u003c/strong\u003eWe developed a local Retrieval-Augmented Generation (RAG) architectureusing a 4-bit quantized Qwen2.5-7B model deployed via the Ollamaframework on a commercial 32\\,GB RAM terminal without a dedicated GPU.To rigorously validate the system, we generated a 2{,}000-casesynthetic baseline of APTT tests and injected 30% semantic and 15%lexical noise to simulate real-world LIS inputs. Output safety wasstrictly enforced utilising Pydantic V2 schemas and a Tenacity-drivenself-reflection mechanism (maximum 3 retries).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eResults:\u003c/strong\u003eThe proposed LLM-RAG middleware demonstrated exceptional robustness,maintaining a Guideline Concordance Accuracy (\\((ACC_{gc})\\)) of 97.00%under high-dimensional noise, whereas the traditional rule-basedbaseline collapsed to 10.00%. The system successfully constrainedhallucinations, recording a Critical Violation Rate (CVR) of only1.50%. Clinical and hardware viability were proven with a throughputof 1.45\\,RPS and an average latency of 1.38\\,seconds (strictly belowthe 3.0\\,s threshold), while achieving a Cohen's Kappa score of 0.88in an independent AI-as-Expert adjudication protocol.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConclusion:\u003c/strong\u003eThis edge-deployed LLM paradigm provides a highly reliable,zero-marginal-cost alternative for LIS modernisation, enabling secureand robust AI integration in resource-constrained medical environments.\u003c/p\u003e","manuscriptTitle":"Privacy-PreservingLLM Middleware in LIS: Edge-Computing for Coagulation InterpretationUnder High-Dimensional Noise","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-23 00:54:16","doi":"10.21203/rs.3.rs-9171815/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":"824a0258-3f7f-4c86-a507-be88a68fbbf1","owner":[],"postedDate":"March 23rd, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-04-08T02:25:15+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-23 00:54:16","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9171815","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9171815","identity":"rs-9171815","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}