{"paper_id":"4ddacbf6-88f7-441e-8a55-a5ca3c4e7936","body_text":"AEGIS: An Operational Infrastructure for Post-Market Governance of Adaptive Medical AI Under US and EU Regulatory Frameworks | 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 AEGIS: An Operational Infrastructure for Post-Market Governance of Adaptive Medical AI Under US and EU Regulatory Frameworks Fardin Afdideh, Mehdi Astaraki, Fernando Seoane, Farhad Abtahi This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9199100/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 Machine learning systems deployed in medical devices require governance frameworks that ensure safety while enabling continuous improvement. Regulatory bodies including the FDA and European Union have introduced mechanisms such as the Predetermined Change Control Plan (PCCP) and Post-Market Surveillance (PMS) to manage iterative model updates without repeated submissions. This paper presents AI/ML Evaluation and Governance Infrastructure for Safety (AEGIS), a governance framework applicable to any healthcare AI system. AEGIS comprises three modules, i.e., dataset assimilation and retraining, model monitoring, and conditional decision, that operationalize FDA PCCP and EU AI Act Article 43(4) provisions. We implement a four-category deployment decision taxonomy (APPROVE, CONDITIONAL APPROVAL, CLINICAL REVIEW, REJECT) with an independent PMS ALARM signal, enabling detection of the critical state in which no deployable model exists while the released model is simultaneously at risk. To illustrate how AEGIS can be instantiated across heterogeneous clinical contexts, we provide two examples: sepsis prediction from electronic health records and brain tumor segmentation from medical imaging. Both cases use identical governance architecture, differing only in configuration. Across 11 simulated iterations on the sepsis example, AEGIS yielded 8 APPROVE, 1 CONDITIONAL APPROVAL, 1 CLINICAL REVIEW, and 1 REJECT decision, exercising all four categories. ALARM signals were co-issued at iterations 8 and 10, including the critical state where no deployable model exists and the released model is simultaneously failing. AEGIS detected drift before observable performance degradation. These results demonstrate that AEGIS translates regulatory change-control concepts into executable governance procedures, supporting safe continuous learning for adaptive medical AI across diverse clinical applications. Artificial Intelligence and Machine Learning AI/ML Evaluation and Governance Infrastructure for Safety (AEGIS) ML/AI-enabled Medical Device (MLMD) Model Adaptation Medical Devices Regulation (MDR) Model Governance Predetermined Change Control Plan (PCCP) EU AI Act Food and Drug Administration (FDA) Post-Market Surveillance (PMS) Total Product Lifecycle (TPLC) Full Text Additional Declarations The authors declare no competing interests. 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-9199100\",\"acceptedTermsAndConditions\":true,\"allowDirectSubmit\":true,\"archivedVersions\":[],\"articleType\":\"Research Article\",\"associatedPublications\":[],\"authors\":[{\"id\":610609531,\"identity\":\"4e56c571-38f8-41f0-84f4-cbad179e75ea\",\"order_by\":0,\"name\":\"Fardin Afdideh\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Karolinska Institutet\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Fardin\",\"middleName\":\"\",\"lastName\":\"Afdideh\",\"suffix\":\"\"},{\"id\":610610281,\"identity\":\"462d29a1-3119-4ea5-8b36-8a709c53af9f\",\"order_by\":1,\"name\":\"Mehdi Astaraki\",\"email\":\"\",\"orcid\":\"https://orcid.org/0000-0001-5125-4682\",\"institution\":\"Karolinska Institutet\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Mehdi\",\"middleName\":\"\",\"lastName\":\"Astaraki\",\"suffix\":\"\"},{\"id\":610610994,\"identity\":\"1dd5ca09-f9d8-4189-ae74-8531ce9eaabd\",\"order_by\":2,\"name\":\"Fernando Seoane\",\"email\":\"\",\"orcid\":\"https://orcid.org/0000-0002-6995-967X\",\"institution\":\"Karolinska Institutet\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Fernando\",\"middleName\":\"\",\"lastName\":\"Seoane\",\"suffix\":\"\"},{\"id\":610608838,\"identity\":\"e409b22a-ed51-41e9-afad-1dc196f647f5\",\"order_by\":3,\"name\":\"Farhad Abtahi\",\"email\":\"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA4klEQVRIie2OvQrCMBRGrwi3SyTrLRV8hbrYRemrtBTi0rk4OAhCJh9BfIZOlW6CUBd/XqEunRycxEUwRcQt1c0hhxAy5HA+AIPhD7FmgFAft76DScAaFbZ5K1gr+5+VlgyahzHrUJX3BHpeb16V55XoAt9u9Aobe/3FEfq5RM8Ns5gBCX3KB4HUkdBKCxhQmE2Uwlx9hVdoPyT4aWHdKFwqhZ+ueoUEOqoSpgVTlZkaBrHWUEqFTvdIUS7jhIJCMCTRNEygfUmGo3V7l9n3aeRzvi31mRf0eeI3/w0Gg8Gg5wmUCjp0hb/zagAAAABJRU5ErkJggg==\",\"orcid\":\"https://orcid.org/0000-0001-7807-8682\",\"institution\":\"Karolinska Institutet\",\"correspondingAuthor\":true,\"prefix\":\"\",\"firstName\":\"Farhad\",\"middleName\":\"\",\"lastName\":\"Abtahi\",\"suffix\":\"\"}],\"badges\":[],\"createdAt\":\"2026-03-23 10:23:57\",\"currentVersionCode\":1,\"declarations\":{\"humanSubjects\":false,\"vertebrateSubjects\":false,\"conflictsOfInterestStatement\":false,\"humanSubjectEthicalGuidelines\":false,\"humanSubjectConsent\":false,\"humanSubjectClinicalTrial\":false,\"humanSubjectCaseReport\":false,\"vertebrateSubjectEthicalGuidelines\":false},\"doi\":\"10.21203/rs.3.rs-9199100/v1\",\"doiUrl\":\"https://doi.org/10.21203/rs.3.rs-9199100/v1\",\"draftVersion\":[],\"editorialEvents\":[],\"editorialNote\":\"\",\"failedWorkflow\":false,\"files\":[{\"id\":105283643,\"identity\":\"77aa5d6c-51a7-4bd6-a6f7-92230bbd0c09\",\"added_by\":\"auto\",\"created_at\":\"2026-03-24 10:43:06\",\"extension\":\"pdf\",\"order_by\":1,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"manuscript-pdf\",\"size\":1397002,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"PCCPManuscriptLaTeXREVISED27.pdf\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-9199100/v1_covered_40e14dcd-332e-45e1-9178-a838b9d90c18.pdf\"}],\"financialInterests\":\"The authors declare no competing interests.\",\"formattedTitle\":\"\\u003cp\\u003eAEGIS: An Operational Infrastructure for Post-Market Governance of Adaptive Medical AI Under US and EU Regulatory Frameworks\\u003c/p\\u003e\",\"fulltext\":[],\"fulltextSource\":\"\",\"fullText\":\"\",\"funders\":[],\"hasAdminPriorityOnWorkflow\":false,\"hasManuscriptDocX\":false,\"hasOptedInToPreprint\":true,\"hasPassedJournalQc\":\"\",\"hasAnyPriority\":true,\"hideJournal\":true,\"highlight\":\"\",\"institution\":\"Karolinska Institute\",\"isAcceptedByJournal\":false,\"isAuthorSuppliedPdf\":true,\"isDeskRejected\":\"\",\"isHiddenFromSearch\":false,\"isInQc\":false,\"isInWorkflow\":false,\"isPdf\":true,\"isPdfUpToDate\":true,\"isWithdrawnOrRetracted\":false,\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"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\":\"AI/ML Evaluation and Governance Infrastructure for Safety (AEGIS), ML/AI-enabled Medical Device (MLMD), Model Adaptation, Medical Devices Regulation (MDR), Model Governance, Predetermined Change Control Plan (PCCP), EU AI Act, Food and Drug Administration (FDA), Post-Market Surveillance (PMS), Total Product Lifecycle (TPLC)\",\"lastPublishedDoi\":\"10.21203/rs.3.rs-9199100/v1\",\"lastPublishedDoiUrl\":\"https://doi.org/10.21203/rs.3.rs-9199100/v1\",\"license\":{\"name\":\"CC BY 4.0\",\"url\":\"https://creativecommons.org/licenses/by/4.0/\"},\"manuscriptAbstract\":\"\\u003cp\\u003eMachine learning systems deployed in medical devices require governance frameworks that ensure safety while enabling continuous improvement. Regulatory bodies including the FDA and European Union have introduced mechanisms such as the Predetermined Change Control Plan (PCCP) and Post-Market Surveillance (PMS) to manage iterative model updates without repeated submissions. This paper presents AI/ML Evaluation and Governance Infrastructure for Safety (AEGIS), a governance framework applicable to any healthcare AI system. AEGIS comprises three modules, i.e., dataset assimilation and retraining, model monitoring, and conditional decision, that operationalize FDA PCCP and EU AI Act Article 43(4) provisions. We implement a four-category deployment decision taxonomy (APPROVE, CONDITIONAL APPROVAL, CLINICAL REVIEW, REJECT) with an independent PMS ALARM signal, enabling detection of the critical state in which no deployable model exists while the released model is simultaneously at risk.\\u003c/p\\u003e\\n\\u003cp\\u003eTo illustrate how AEGIS can be instantiated across heterogeneous clinical contexts, we provide two examples: sepsis prediction from electronic health records and brain tumor segmentation from medical imaging. Both cases use identical governance architecture, differing only in configuration. Across 11 simulated iterations on the sepsis example, AEGIS yielded 8 APPROVE, 1 CONDITIONAL APPROVAL, 1 CLINICAL REVIEW, and 1 REJECT decision, exercising all four categories. ALARM signals were co-issued at iterations 8 and 10, including the critical state where no deployable model exists and the released model is simultaneously failing. AEGIS detected drift before observable performance degradation. These results demonstrate that AEGIS translates regulatory change-control concepts into executable governance procedures, supporting safe continuous learning for adaptive medical AI across diverse clinical applications.\\u003c/p\\u003e\",\"manuscriptTitle\":\"AEGIS: An Operational Infrastructure for Post-Market Governance of Adaptive Medical AI Under US and EU Regulatory Frameworks\",\"msid\":\"\",\"msnumber\":\"\",\"nonDraftVersions\":[{\"code\":1,\"date\":\"2026-03-24 10:42:22\",\"doi\":\"10.21203/rs.3.rs-9199100/v1\",\"editorialEvents\":[{\"type\":\"communityComments\",\"content\":0}],\"status\":\"published\",\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"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\":\"0561574a-00df-49d1-a59e-ad96b8a44f74\",\"owner\":[],\"postedDate\":\"March 24th, 2026\",\"published\":true,\"recentEditorialEvents\":[],\"rejectedJournal\":[],\"revision\":\"\",\"amendment\":\"\",\"status\":\"posted\",\"subjectAreas\":[{\"id\":64962476,\"name\":\"Artificial Intelligence and Machine Learning\"}],\"tags\":[],\"updatedAt\":\"2026-03-24T10:42:22+00:00\",\"versionOfRecord\":[],\"versionCreatedAt\":\"2026-03-24 10:42:22\",\"video\":\"\",\"vorDoi\":\"\",\"vorDoiUrl\":\"\",\"workflowStages\":[]},\"version\":\"v1\",\"identity\":\"rs-9199100\",\"journalConfig\":\"researchsquare\"},\"__N_SSP\":true},\"page\":\"/article/[identity]/[[...version]]\",\"query\":{\"redirect\":\"/article/rs-9199100\",\"identity\":\"rs-9199100\",\"version\":[\"v1\"]},\"buildId\":\"XKTyCvWXoU3ODBz1xrDgd\",\"isFallback\":false,\"isExperimentalCompile\":false,\"dynamicIds\":[84888],\"gssp\":true,\"scriptLoader\":[]}","source_license":"CC-BY-4.0","license_restricted":false}