EviLedger: governing clinical AI with a verifiable evidence ledger

preprint OA: closed
Full text JSON View at publisher
AI-generated summary by claude@2026-07, 2026-07-14

EviLedger is a verifiable evidence ledger that tracks changes in clinical evidence to govern AI decision-making, demonstrating high accuracy in detecting drift and contradictions, reducing citation issues, and improving the efficiency of guideline surveillance.

One-sentence paraphrase of the abstract; not a substitute for reading it. No clinical advice. How this works

AI-generated deep summary by claude@2026-07, 2026-07-14 · read from full text

The paper introduces EviLedger, a clinical AI governance approach that converts guideline changes, drug labels, and EHR events into immutable, hash-linked assertions with rollback support to preserve the “evidence state” behind past AI decisions. Using 2,000 guideline-change events and 1,200 cross-source contradiction cases (Cohen’s κ = 0.87), the system reports drift and contradiction performance (drift F1 94.2%, contradiction F1 94.0%), plus a blinded semantic audit showing 93.7% of extracted assertions are supported by their evidence spans (κ = 0.84) and external validation on ESC/JCS guidelines with F1 >90%. As an auditable memory layer for LLM retrieval, EviLedger is reported to reduce stale and unverifiable citations and to enable p95 rollback within 5.13 s at 78M assertions, with a 6-month hospital pilot detecting more actionable guideline changes with much faster triage; the work is a Research Square preprint and not peer reviewed. The paper does not explicitly discuss endometriosis or adenomyosis; it was included in the corpus via a keyword match in the upstream search index.

Read from the paper's body, not the abstract. Not a substitute for reading the paper. No clinical advice. How this works

Abstract

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.
Full text 9,990 characters · extracted from preprint-html · click to expand
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":[]}

Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy (via DOI) is the canonical version.

My notes (saved in your browser only)

Ask this paper AI returns verbatim quotes from the full text · source: preprint-html

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2026) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.

Source provenance

europepmc
last seen: 2026-05-20T01:45:00.602351+00:00