Journal Article DKFZ-2026-01478

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png
Towards autonomous medical artificial intelligence agents.

 ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;  ;

2026
Nature Publ. Group London [u.a.]

Nature nn, nn () [10.1038/s41586-026-10675-5]
 GO

Abstract: Large language models (LLMs) show great potential for clinical decision-making, yet most applications remain narrow, task-specific chat tools rather than systems integrated into clinical workflows1,2. 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.

Classification:

Note: epub

Contributing Institute(s):
  1. DKTK Koordinierungsstelle Dresden (DD01)
Research Program(s):
  1. 899 - ohne Topic (POF4-899) (POF4-899)

Appears in the scientific report 2026
Database coverage:
Medline ; BIOSIS Previews ; Biological Abstracts ; Chemical Reactions ; Clarivate Analytics Master Journal List ; Current Contents - Agriculture, Biology and Environmental Sciences ; Current Contents - Life Sciences ; Current Contents - Physical, Chemical and Earth Sciences ; DEAL Nature ; Ebsco Academic Search ; Essential Science Indicators ; IF >= 60 ; Index Chemicus ; JCR ; SCOPUS ; Science Citation Index Expanded ; Web of Science Core Collection ; Zoological Record
Click to display QR Code for this record

The record appears in these collections:
Document types > Articles > Journal Article
Public records
Publications database

 Record created 2026-06-18, last modified 2026-06-19



Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)