EviLedger: governing clinical AI with a verifiable evidence ledger

EviLedger: governing clinical AI with a verifiable evidence ledger | 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 EviLedger: governing clinical AI with a verifiable evidence ledger Rui Li, Shuang Cao, Ruihua Liu, Alexandre Duprey This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8769058/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 Clinical evidence evolves, yet most AI systems cannot reconstruct the evidence state supporting a past decision. We introduce EviLedger, an evidence ledger that converts guidelines, drug labels, and EHR events into immutable assertions linked to hashes and rollback. On 2,000 guideline-change events and 1,200 cross-source contradiction cases (Cohen’s κ = 0.87), EviLedger achieves drift F1 94.2% and contradiction F1 94.0%. A blinded semantic audit finds that 93.7% of extracted assertions are semantically supported by their evidence spans (κ = 0.84), and external validation on ESC/JCS guidelines yields F1 >90%. As an auditable memory layer for LLM-based retrieval, EviLedger reduces stale citations from 14.7% to 1.2% and unverifiable citations from 28.4% to 2.3%, while supporting p95 rollback in 5.13 s at 78M assertions. In a 6-month hospital pilot, EviLedger detects 5.5× more actionable guideline changes with 104× faster triage than manual surveillance. Health sciences/Health care/Health services Physical sciences/Mathematics and computing/Computer science evidence ledger clinical governance guideline drift provenance auditable AI Full Text Additional Declarations There is NO Competing Interest. 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-8769058","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":594021005,"identity":"fe66617a-208b-473f-85ab-321b3b36f7a7","order_by":0,"name":"Rui Li","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA20lEQVRIiWNgGAWjYFACxgaGBwY2CWzszA1QER4gNiCgJcEgLYGNmZFoLUCQwHA4gQFVCx5gPiMZaEvB+Tw+Zsa2Dx/+2Mibt589wPCjALcWmRuJIIfdLgY6rHnmzLY0wzln8hIYe/A4TEICoiWxDaiFmbfhMOMMCR4DBh7CWs5BtPz5898epIXxD2EtByBaGNgOJIK0MOO1hedhw4EEg2SwFsbetuTkGTw5Bodl8GlhT3/44MMfu8T57c2HGX78sbOdwX7G8OGbP7i1gMABIkRGwSgYBaNgFJAEAJ6MSocllulrAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0009-0007-6857-2127","institution":"Hill Research","correspondingAuthor":true,"prefix":"","firstName":"Rui","middleName":"","lastName":"Li","suffix":""},{"id":594021006,"identity":"db590a8c-4374-4f63-8712-faa646e6b348","order_by":1,"name":"Shuang Cao","email":"","orcid":"","institution":"Hill Research","correspondingAuthor":false,"prefix":"","firstName":"Shuang","middleName":"","lastName":"Cao","suffix":""},{"id":594021007,"identity":"a2402c91-222f-4fe4-88bf-0ff6a1a1f243","order_by":2,"name":"Ruihua Liu","email":"","orcid":"","institution":"Hill Research","correspondingAuthor":false,"prefix":"","firstName":"Ruihua","middleName":"","lastName":"Liu","suffix":""},{"id":594021008,"identity":"518a5efc-cc80-47d5-b812-bee87b962772","order_by":3,"name":"Alexandre Duprey","email":"","orcid":"","institution":"Hill Research","correspondingAuthor":false,"prefix":"","firstName":"Alexandre","middleName":"","lastName":"Duprey","suffix":""}],"badges":[],"createdAt":"2026-02-02 21:41:10","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8769058/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8769058/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":103088545,"identity":"41b20239-2f50-4d66-a775-58842c69b5b0","added_by":"auto","created_at":"2026-02-20 16:22:50","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":413030,"visible":true,"origin":"","legend":"Article File","description":"","filename":"nmi.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8769058/v1_covered_f39ebe96-65b7-48dc-97a7-279f3c64e8ae.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"EviLedger: governing clinical AI with a verifiable evidence ledger","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":"evidence ledger, clinical governance, guideline drift, provenance, auditable AI","lastPublishedDoi":"10.21203/rs.3.rs-8769058/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8769058/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eClinical evidence evolves, yet most AI systems cannot reconstruct the evidence state supporting a past decision. We introduce EviLedger, an evidence ledger that converts guidelines, drug labels, and EHR events into immutable assertions linked to hashes and rollback.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eOn 2,000 guideline-change events and 1,200 cross-source contradiction cases (Cohen’s κ = 0.87), EviLedger achieves drift F1 94.2% and contradiction F1 94.0%. A blinded semantic audit finds that 93.7% of extracted assertions are semantically supported by their evidence spans (κ = 0.84), and external validation on ESC/JCS guidelines yields F1 \u0026gt;90%. As an auditable memory layer for LLM-based retrieval, EviLedger reduces stale citations from 14.7% to 1.2% and unverifiable citations from 28.4% to 2.3%, while supporting p95 rollback in 5.13 s at 78M assertions. In a 6-month hospital pilot, EviLedger detects 5.5× more actionable guideline changes with 104× faster triage than manual surveillance.\u003c/p\u003e","manuscriptTitle":"EviLedger: governing clinical AI with a verifiable evidence ledger","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-20 16:22:30","doi":"10.21203/rs.3.rs-8769058/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":"3db85637-f94e-4c82-aaad-520d73c18fe1","owner":[],"postedDate":"February 20th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":63214041,"name":"Health sciences/Health care/Health services"},{"id":63214042,"name":"Physical sciences/Mathematics and computing/Computer science"}],"tags":[],"updatedAt":"2026-02-20T16:22:30+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-20 16:22:30","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8769058","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8769058","identity":"rs-8769058","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}