OpenEvidence brings patient-aware clinical AI into NYU Langone’s Epic workflow
OpenEvidence’s Patient Aware Clinical Intelligence will give NYU Langone clinicians answers grounded in patient context and peer-reviewed medical literature without leaving Epic.

AT A GLANCE
Key points
- Clinicians will ask clinical questions in natural language from inside Epic.
- Responses will connect patient context with peer-reviewed medical literature.
- The deployment covers hospitals, the ambulatory network and Family Health Centers.
- The announcement provides no independent accuracy or clinical-outcomes data.
What is changing?
NYU Langone Health and OpenEvidence announced a collaboration to embed Patient Aware Clinical Intelligence in the health system’s Epic electronic health record workflow. Clinical teams will be able to ask complex questions in natural language without leaving Epic, while the system connects responses to patient-record context and peer-reviewed medical literature.
The deployment spans NYU Langone hospitals, its ambulatory network and Family Health Centers. The organization reports 12.4 million outpatient visits and more than 421,000 emergency-department visits each year. Those figures describe the scale of the health system the integration can reach; they do not mean the tool will be used at every visit or improve clinical outcomes.
The announcement says responses will be sourced and literature-grounded, but it does not provide an independent accuracy rate, error rate or outcomes study. Clinical teams still need to verify recommendations against primary sources, limit access to patient data and keep final decisions with qualified healthcare professionals.
Explore the original sources
Source date: 29 October 2026.
Published by AI Radar: 29 Oct 2026, 20:59 (Istanbul, UTC+3).
FOLLOW THE TOPIC
Topics and tags
Share your discovery.
Send this story to a friend.
Reader comments
What do you think about this development? Share your experience or question. Comments are published after editorial approval.
Your name/nickname and comment become public if approved. Read: Privacy notice.






Loading comments…