ChatEHR (Stanford Medicine)

By Stanford Medicine
· USA
In-house generative AI assistant embedded in the electronic health record, letting clinicians ask questions about a patient’s chart and get summaries.
RAG / Knowledge AI
Clinical Documentation
Pilot
Regulatory status
Deployment
Pilot
Clinical role
Adjunct (decision support)
Headquarters
USA
AI type
RAG / Knowledge AI

Precise indication

Clinicians reviewing patient records. A large language model integrated into the EHR answers questions and summarises the chart. Stanford states it is an information tool, not a source of medical advice.

Regulatory status

Developed internally by Stanford Medicine and Stanford Health Care. Not presented as a medical device in the sources reviewed (November 2026).

Clinical evidence

Vendor-supported
Independent

Real-world deployment

Pilot with 33 clinicians at Stanford Hospital, announced June 2025, with a wider rollout to clinicians who review charts planned.

Interoperability

European status

Editorial verdict

Limits and uncertainties

– Pilot stage only; no published accuracy, safety or time-saving data identified.
– Generative AI can produce incorrect or unsupported statements (hallucinations); outputs must be checked against the record.
– Underlying model, hosting and data-protection set-up are not detailed in the public source.

Sources

News, Stanford Medicine, ChatEHR, June 2025: https://med.stanford.edu/news/all-news/2025/06/chatehr.html

This profile is not medical advice or an endorsement. Hospitals should perform their own due diligence (regulatory compliance, GDPR, cybersecurity, integration, local clinical validation). How we evaluate

At a glance
Vendor
Stanford Medicine
Headquarters
USA
AI type
RAG / Knowledge AI
Clinical role
Adjunct (decision support)
CE marking
Notified body
EU AI Act
Data hosting
Last verified
Reviewed by
How we evaluate

Every profile documents the precise indication, regulatory status, vendor-supported and independent evidence, real-world deployment, limits and dated sources.

A independent systematic review or prospective multicentre study · B at least one independent peer-reviewed study · C peer-reviewed, vendor-supported · D vendor claims only.

Read the methodology →

Spotted an error?

Vendors, authors and clinicians can request a correction. Corrections are dated on the profile.