# Towards autonomous medical artificial intelligence agents

- **DOI:** [10.1038/s41586-026-10675-5](https://doi.org/10.1038/s41586-026-10675-5)
- **Rating:** Strong (3.8 out of 5)
- **Verdict:** MIRA advances EHR-integrated clinical AI with broad simulated validation, but real-world deployment remains untested.
- **Framework version:** v5.0
- **Pipeline version:** v0.4
- **Evaluation date:** 2026-06-19
- **Evaluation page:** https://www.nabu.science/paper/10.1038%2Fs41586-026-10675-5

## Strengths

- **End-to-end EHR workflow evaluation** MIRA is evaluated as a tool-using agent inside a FHIR-compliant sandbox rather than as a standalone chat model. The workflow includes patient dialogue, physical examination lookup, laboratory, microbiology and imaging requests, diagnosis, medication prescribing, procedure search, and admission decisions.
  - Dimension: contribution
  - Location: Fig. 1; Introduction, pp. 1–2
- **Broad multi-axis clinical assessment** The study does not rely on diagnostic accuracy alone. It evaluates patient-agent robustness, diagnostic test selection, procedure matching, guideline adherence, medication safety, admission decisions, and perturbation robustness across multiple figures and supplementary tables.
  - Dimension: methodological rigour
  - Location: Figs. 2–5; Supplementary Data Tables 1–43
- **Explicit limitations and deployment framing** The Discussion acknowledges simulated patient interactions, possible MIMIC-IV training overlap, physician cohort limitations, and the need for prospective validation. It frames near-term use as supervised assistance for bounded tasks rather than replacing clinicians.
  - Dimension: positioning
  - Location: Discussion, pp. 9–10

## Limitations

- **Single-source retrospective simulation limits generalization** All main cases derive from MIMIC-IV, a single-institution public EHR dataset, and patient conversations are simulated from HPI text rather than real patient encounters. The paper itself notes that this may overestimate generalization to other cases.
  - Dimension: methodological rigour
  - Location: Methods, MIMIC-IV dataset; Discussion, pp. 9–10
- **Reproducibility materials are incomplete** The supplied text does not show public release of the MIRA implementation, prompts, model details, weights, or complete sandbox execution environment. This limits independent verification of the reported agent performance.
  - Dimension: methodological rigour
  - Location: Methods; article text supplied
- **Clinical comparison samples remain small** The head-to-head physician comparison uses four board-certified physicians and a six-person mixed-seniority cohort, while the medication safety review covers 56 patients. These samples are useful for proof-of-concept evaluation but limit strong claims about physician-level clinical performance and safety.
  - Dimension: application pathway
  - Location: Introduction, p. 2; Fig. 5a; Discussion, p. 10

## Reliability checks

Caveats (4 of 4 checks).

- **Internal coherence:** Noted. The article is numerically coherent on its main results and clearly distinguishes the full MIMIC-IV evaluation from the physician-comparison subset. The main internal-coherence watch-out is interpretive framing: autonomy and physician-level claims are stronger than the retrospective sandbox design can fully support.
- **Research conduct:** Noted. The study uses a public credentialed EHR dataset and provides substantial procedural detail, but independent verification is limited by absent public code/model details and lack of visible ethics or COI declarations in the supplied text. Potential MIMIC-IV overlap with LLM training data is acknowledged and remains a conduct-relevant interpretive watch-out.
- **Reference integrity:** Clean. All 26 cited references resolved to real publications via PubMed, Crossref, or OpenAlex.
  - References not verified automatically are resolved manually within 24 hours.

## Post-publication record

- **Status:** Clean
- **Summary:** No retraction or expression of concern found in Crossref (includes Retraction Watch).
- **Last checked:** 2026-10-17
