Towards autonomous medical artificial intelligence agents
. However, building physician copilots will require models that operate within the electronic health record (EHR), with governed access to patient data and the ability to initiate permitted EHR actions within defined safety constraints. Yet it remains unproven whether such a system can manage patient cases with physician-level performance. Here we show that MIRA (Medical Intelligence for Reasoning and Action), an autonomous artificial intelligence agent operating in a sandboxed EHR environment, can navigate a large clinical action space to obtain patient histories; order and interpret laboratory, imaging and microbiology tests; generate differential diagnoses; and formulate treatment plans such as prescribing medications, scheduling surgical procedures and planning admissions. In simulations on real patient cases spanning multiple diagnoses, MIRA outperformed physicians in diagnostic accuracy and made guideline-concordant, medication-safe and appropriate admission decisions. Compared with previous LLM applications that addressed isolated subtasks or provided free-text advice, these results suggest that an EHR-integrated artificial intelligence agent can turn clinical intent into structured, actionable EHR operations, possibly making it a more effective decision-support partner for physicians. Further work is needed to establish generalization, safety and governance through prospective, real-world studies.
Authors
- Daniel Truhn (ORCID: https://orcid.org/0000-0002-9605-0728)
- Marius Bill (ORCID: https://orcid.org/0000-0002-1175-2406)
- Jan‐Niklas Eckardt (ORCID: https://orcid.org/0000-0002-3649-2823)
- Benedict Kinny‐Köster (ORCID: https://orcid.org/0009-0003-7040-9725)
- Jan Moritz Middeke (ORCID: https://orcid.org/0000-0003-3250-293X)
- Jan Clusmann (ORCID: https://orcid.org/0000-0003-2925-8438)
- Katharina Egger‐Heidrich (ORCID: https://orcid.org/0000-0002-0472-4335)
- Dyke Ferber (ORCID: https://orcid.org/0009-0006-6195-9276)
- A J. Iafrate
- Lars Hilgers
- Georg Wölflein (ORCID: https://orcid.org/0000-0002-0407-7617)
- Maximilian Mayrhofer‐Schmid (ORCID: https://orcid.org/0000-0003-2184-8337)
- Jakob Nikolas Kather (ORCID: https://orcid.org/0000-0002-3730-5348)
- Alexander Oeser (ORCID: https://orcid.org/0000-0003-3767-6437)
- Dirk Jaeger (ORCID: https://orcid.org/0000-0002-1276-7802)
- Christiane Höper
- Marcel Oehme
- Martin Schneider (ORCID: https://orcid.org/0000-0002-5501-4050)
- Isabella C. Wiest
- Lejla Kadric
Institutions
- German Cancer Research Center (DE)
- Heidelberg University (DE)
- University Hospital Heidelberg (DE)
- NYU Langone Health (US)
- Massachusetts General Hospital (US)
- Fresenius (Germany) (DE)
- Unfallkrankenhaus Berlin (DE)
- National Center for Tumor Diseases (DE)
- Universitätsklinikum Aachen (DE)
- Center for Cancer Research (US)
- University Hospital Carl Gustav Carus (DE)
- Technische Universität Dresden (DE)
- RWTH Aachen University (DE)
- Leipzig University (DE)
Publication Details
- Journal
- Nature
- Published
- 2026-06-17
- DOI
- https://doi.org/10.1038/s41586-026-10675-5
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00