{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T09:29:20Z","timestamp":1787131760586,"version":"build-2736575974"},"reference-count":52,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T00:00:00Z","timestamp":1787097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100009377","name":"Education Department of Hunan Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100009377","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Cardiovasc. Med."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Cardiovascular medicine faces persistent implementation gaps driven by workforce shortages, fragmented data systems, and the cognitive burden of complex clinical decision-making\u2014structural constraints that limit the delivery of guideline-directed care. Artificial intelligence (AI) is transitioning from isolated predictive models toward autonomous agent systems capable of perceiving, reasoning, and acting in clinical environments, offering a potential pathway to address these challenges.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This review synthesizes current evidence on AI agent systems in cardiovascular medicine across four interconnected dimensions: technical paradigms enabling agentic functionality (multi-agent systems, digital twins, multimodal integration), emerging clinical applications across the cardiovascular continuum, and governance frameworks essential for responsible translation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We conducted a narrative review of peer-reviewed literature published between January 2020 and March 2026, drawing from PubMed, Web of Science, IEEE Xplore, and Scopus databases. Search terms included combinations of \u201cartificial intelligence\u201d, \u201cAI agents\u201d, \u201cautonomous agents\u201d, \u201cmulti-agent systems\u201d, \u201clarge language models\u201d, \u201ccardiovascular diseases\u201d, \u201cheart failure\u201d, \u201cdigital twins\u201d, and \u201cclinical decision support\u201d. Emphasis was placed on high-quality original research, systematic reviews, and position papers from major cardiovascular societies, with particular attention to developments from 2024 to 2026.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Agentic AI systems should function as augmented intelligence\u2014enhancing rather than replacing clinical judgment\u2014to close implementation gaps in cardiovascular care. Multi-agent architectures, digital cardiovascular twins, and multimodal integration are emerging as core technical paradigms. The ClinNoteAgents system demonstrates high extraction fidelity (conditional accuracy \u226590%) for clinical variables while achieving 60%\u201390% text reduction. Digital twin applications span therapy planning, risk prediction, and monitoring, with 69% relying on mechanistic models and 76% utilizing imaging data for personalization. Heart failure has emerged as a paradigmatic use case, driven by structural workforce gaps and the ARPA-H ADVOCATE initiative launched in January 2026. The C.A.R.D.I.O. framework (Clinical validation, Auditability, Risk stratification, Data privacy, Integration, Ongoing vigilance) and the CURACO framework (Clinical safety, Understanding, Research-informed care, Authentic patient-centred approaches, Conscientious ethics, Optimised technology) provide governance structures for responsible deployment. A rapid systematic review of 13 studies including 22,641 participants found that 85% of AI interventions improved cardiovascular outcomes, with mortality reductions of 0.8%\u201312% and major adverse cardiovascular event reductions of 4%\u201312%.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Cardiovascular medicine stands at an inflection point. The transition from assistance to autonomy requires rigorous fit-for-purpose evaluation, transparent interpretability mechanisms, and robust governance frameworks. Agentic AI systems should function as augmented intelligence\u2014enhancing rather than replacing clinical judgment\u2014to close implementation gaps in cardiovascular care.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fcvm.2026.1838415","type":"journal-article","created":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T09:10:11Z","timestamp":1787130611000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["From assistance to autonomy: AI agent systems in cardiovascular medicine\u2014a review of paradigms, architectures, and clinical translation"],"prefix":"10.3389","volume":"13","author":[{"given":"Ye","family":"Chen","sequence":"first","affiliation":[{"name":"School of Information Science and Engineering, Hunan International Economics University","place":["Changsha, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoqun","family":"Qin","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Hunan International Economics University","place":["Changsha, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shouping","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Hunan International Economics University","place":["Changsha, China"]},{"name":"Hunan Nianlun Orthopaedic Hospital Group","place":["Changsha, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,19]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"2350","DOI":"10.1016\/j.jacc.2023.11.007","article-title":"Global burden of cardiovascular diseases and risks, 1990\u20132022","volume":"82","author":"Mensah","year":"2023","journal-title":"J Am Coll Cardiol"},{"key":"B2","doi-asserted-by":"publisher","first-page":"2361","DOI":"10.1016\/j.jacc.2022.11.005","article-title":"The global burden of cardiovascular diseases and risk: a compass for future health","volume":"80","author":"Vaduganathan","year":"2022","journal-title":"J Am Coll Cardiol"},{"key":"B3","doi-asserted-by":"publisher","first-page":"3227","DOI":"10.1093\/eurheartj\/ehab484","article-title":"2021 ESC guidelines on cardiovascular disease prevention in clinical practice","volume":"42","author":"Visseren","year":"2021","journal-title":"Eur Heart J"},{"key":"B4","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1080\/00015385.2025.2576441","article-title":"Belgian position paper on implementing artificial intelligence in cardiology: a roadmap from theory to clinical practice","volume":"81","author":"Dujardin","year":"2025","journal-title":"Acta Cardiol"},{"key":"B5","first-page":"1234","article-title":"Artificial intelligence-electrocardiogram performance across diverse image formats","volume":"85","author":"Dhingra","year":"2025","journal-title":"J Am Coll Cardiol"},{"key":"B6","first-page":"789","article-title":"Deep learning for cardiovascular medicine: a review of current applications","volume":"85","author":"Krittanawong","year":"2025","journal-title":"J Am Coll Cardiol"},{"key":"B7","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1038\/s41586-020-2145-8","article-title":"Video-based AI for beat-to-beat assessment of cardiac function","volume":"580","author":"Ouyang","year":"2024","journal-title":"Nature"},{"key":"B8","doi-asserted-by":"publisher","first-page":"1789","DOI":"10.1097\/MS9.0000000000004607","article-title":"Artificial intelligence in cardiology: an updated systematic review with ethical considerations and challenges in implementing artificial intelligence models","volume":"88","author":"Patel","year":"2026","journal-title":"Ann Med Surg"},{"key":"B9","doi-asserted-by":"publisher","first-page":"691","DOI":"10.1016\/j.jacc.2025.07.040","article-title":"Moving beyond the model: our perspective on meaningful AI research in cardiovascular care","volume":"86","author":"Jain","year":"2025","journal-title":"J Am Coll Cardiol"},{"key":"B10","doi-asserted-by":"publisher","first-page":"102374","DOI":"10.1016\/j.xcrm.2025.102374","article-title":"A foundational architecture for AI agents in healthcare","volume":"6","author":"Liu","year":"2025","journal-title":"Cell Rep Med"},{"key":"B11","year":""},{"key":"B12","doi-asserted-by":"crossref","first-page":"103599","DOI":"10.1016\/j.inffus.2025.103599","article-title":"AI Agents vs. agentic AI: a conceptual taxonomy, applications and challenges","volume":"126","author":"Sapkota","year":"2026","journal-title":"Inf Fusion"},{"key":"B13","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","article-title":"Large language models encode clinical knowledge","volume":"620","author":"Singhal","year":"2024","journal-title":"Nature"},{"key":"B14","volume-title":"Developing Intelligent Health Agents to Drive a Paradigm Shift in Healthcare","year":"2026"},{"key":"B15","first-page":"1012","article-title":"Parallel hospitals and digital twins: the future of healthcare systems","volume":"55","author":"Wang","year":"2025","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"key":"B16","author":"Zhou","year":""},{"key":"B17","author":"Zhou","year":""},{"key":"B18","year":""},{"key":"B19","author":"Zhou","year":""},{"key":"B20","doi-asserted-by":"publisher","first-page":"e202601","DOI":"10.21542\/gcsp.2026.9","article-title":"Reimagining cardiac care with AI, LLMs, blockchain, and metaverse: an integrated framework","volume":"2026","author":"Musamih","year":"2026","journal-title":"Glob Cardiol Sci Pract"},{"key":"B21","doi-asserted-by":"publisher","first-page":"5272","DOI":"10.3390\/s25175272","article-title":"Digital cardiovascular twins, AI agents, and sensor data: a narrative review from system architecture to proactive heart health","volume":"25","author":"Tasmurzayev","year":"2025","journal-title":"Sensors"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1633539","DOI":"10.3389\/fdgth.2025.1633539","article-title":"Digital twins in healthcare: a comprehensive review and future directions","volume":"7","author":"Khoshfekr Rudsari","year":"2025","journal-title":"Front Digit Health"},{"key":"B23","year":""},{"key":"B24","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1038\/s41746-022-00640-7","article-title":"The health digital twin to tackle cardiovascular disease\u2014a review of an emerging technology","volume":"5","author":"Coorey","year":"2022","journal-title":"NPJ Digit Med"},{"key":"B25","doi-asserted-by":"publisher","first-page":"4556","DOI":"10.1093\/eurheartj\/ehaa159","article-title":"The \u2018digital twin\u2019 to enable the vision of precision cardiology","volume":"41","author":"Corral-Acero","year":"2024","journal-title":"Eur Heart J"},{"key":"B26","doi-asserted-by":"publisher","first-page":"672","DOI":"10.1097\/CM9.0000000000004000","article-title":"Integrating multimodal intelligence in heart failure: AI-driven risk prediction, precision diagnosis, phenotyping, personalized treatment, and prognosis","volume":"139","author":"Zhang","year":"2026","journal-title":"Chin Med J"},{"key":"B27","doi-asserted-by":"publisher","first-page":"1678","DOI":"10.1016\/j.jacc.2025.07.053","article-title":"A fully automated echocardiogram interpretation system","volume":"85","author":"Zhang","year":"2025","journal-title":"J Am Coll Cardiol"},{"key":"B28","doi-asserted-by":"publisher","first-page":"390","DOI":"10.3390\/diagnostics16030390","article-title":"Large language models in cardiovascular prevention: a narrative review and governance framework","volume":"16","author":"Santos","year":"2026","journal-title":"Diagnostics"},{"key":"B29","doi-asserted-by":"publisher","first-page":"1094","DOI":"10.1016\/j.jacc.2025.12.027","article-title":"When care becomes autonomous: the ADVOCATE initiative and the future of heart failure management","volume":"87","author":"Krumholz","year":"2026","journal-title":"J Am Coll Cardiol"},{"key":"B30","first-page":"e256","article-title":"Machine learning for subtype definition and risk prediction in heart failure","volume":"7","author":"Banerjee","year":"2025","journal-title":"Lancet Digit Health"},{"key":"B31","doi-asserted-by":"publisher","first-page":"4370827","DOI":"10.1161\/circ.152.suppl_3.4370827","article-title":"Artificial intelligence intervention versus standard care in cardiovascular disease outcomes: a rapid systematic review","volume":"152","author":"Adu","year":"2025","journal-title":"Circulation"},{"key":"B32","first-page":"25","article-title":"Artificial intelligence-enhanced electrocardiography in cardiovascular disease management","volume":"22","author":"Siontis","year":"2025","journal-title":"Nat Rev Cardiol"},{"key":"B33","doi-asserted-by":"publisher","first-page":"ztaf143.169","DOI":"10.1093\/ehjdh\/ztaf143.169","article-title":"AI-derived ACS checklists for cardiology training: implementation barriers and ethical considerations using the CURACO framework","volume":"7","author":"Sooltan","year":"2026","journal-title":"Eur Heart J Digit Health"},{"key":"B34","doi-asserted-by":"publisher","first-page":"789","DOI":"10.1186\/s12912-025-03594-9","article-title":"Generative artificial intelligence in cardiovascular specialty care: a scoping review","volume":"24","author":"Zheng","year":"2025","journal-title":"BMC Nurs"},{"key":"B35","first-page":"234","article-title":"Embodied intelligence in vascular intervention: from perception to action\u2014a technological evolution","volume":"18","author":"Qi","year":"2025","journal-title":"IEEE Rev Biomed Eng"},{"key":"B36","doi-asserted-by":"publisher","first-page":"145","DOI":"10.3390\/diagnostics16010145","article-title":"Application of telemedicine and artificial intelligence in outpatient cardiology care: teleAI-CVD study","volume":"16","author":"Toth","year":"2026","journal-title":"Diagnostics"},{"key":"B37","doi-asserted-by":"crossref","first-page":"ztag019","DOI":"10.1093\/ehjdh\/ztag019","article-title":"Total product lifecycle regulatory considerations and recommendations for generative AI-enabled medical devices","volume":"7","author":"Armoundas","year":"2026","journal-title":"Eur Heart J Digit Health"},{"key":"B38","year":""},{"key":"B39","year":""},{"key":"B40","year":""},{"key":"B41","year":""},{"key":"B42","first-page":"689","article-title":"Human-centered AI in healthcare: a framework for transparency and trust","volume":"333","author":"Barry","year":"2025","journal-title":"J Am Med Assoc"},{"key":"B43","first-page":"1","article-title":"A governance model for AI in healthcare","volume":"7","author":"Reddy","year":"2024","journal-title":"NPJ Digit Med"},{"key":"B44","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12916-019-1426-2","article-title":"Key challenges for delivering clinical impact with artificial intelligence","volume":"22","author":"Kelly","year":"2024","journal-title":"BMC Med"},{"key":"B45","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s41591-019-0548-6","article-title":"Do no harm: a roadmap for responsible machine learning for health care","volume":"30","author":"Wiens","year":"2024","journal-title":"Nat Med"},{"key":"B46","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1136\/bmjqs-2018-008370","article-title":"Artificial intelligence, bias and clinical safety","volume":"33","author":"Challen","year":"2024","journal-title":"BMJ Qual Saf"},{"key":"B47","doi-asserted-by":"publisher","first-page":"822","DOI":"10.1126\/science.adk6139","article-title":"As artificial intelligence goes multimodal, medical applications multiply","volume":"387","author":"Topol","year":"2025","journal-title":"Science"},{"key":"B48","first-page":"67","article-title":"Implementing machine learning in health care\u2014addressing ethical challenges","volume":"392","author":"Char","year":"2025","journal-title":"N Engl J Med"},{"key":"B49","first-page":"e235098","article-title":"Ethical limitations of algorithmic fairness solutions in health care","volume":"5","author":"McCradden","year":"2024","journal-title":"JAMA Health Forum"},{"key":"B50","first-page":"239","article-title":"The global landscape of AI ethics guidelines","volume":"6","author":"Jobin","year":"2024","journal-title":"Nat Mach Intell"},{"key":"B51","first-page":"e247","article-title":"The imperative for regulatory oversight of large language models in health care","volume":"6","author":"Mesk\u00f3","year":"2024","journal-title":"Lancet Digit Health"},{"key":"B52","doi-asserted-by":"publisher","first-page":"e0001029","DOI":"10.1371\/journal.pdig.0001029","article-title":"Cardiology knowledge assessment of retrieval-augmented open versus proprietary large language models","volume":"5","author":"Tarabanis","year":"2026","journal-title":"PLoS Digit Health"}],"container-title":["Frontiers in Cardiovascular Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcvm.2026.1838415\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T09:10:15Z","timestamp":1787130615000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcvm.2026.1838415\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,19]]},"references-count":52,"alternative-id":["10.3389\/fcvm.2026.1838415"],"URL":"https:\/\/doi.org\/10.3389\/fcvm.2026.1838415","relation":{},"ISSN":["2297-055X"],"issn-type":[{"value":"2297-055X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,19]]},"article-number":"1838415"}}