OpenEvidence Joins NYU Langone Epic Workflow for 12 Million Visits

OpenEvidence will sit inside NYU Langone's Epic electronic health record system, bringing patient-aware clinical intelligence to about 12 million visits across New York City's largest academic health system.

Christopher Ort
By Christopher Ort · 6 min read
Share
A hospital corridor at dusk with soft overhead lighting, a nurse station in the background, and a computer workstation in the foreground showing a blurred electronic health record interface.
Image: AI-generated, i10X
On this page
  1. Quick Take
  2. In plain English
  3. What happened
  4. The integration
  5. Why it matters
  6. What's still open
  7. About the analysis
  8. i10x Perspective

OpenEvidence, the AI clinical decision support platform used by millions of U.S. physicians, will now sit directly inside NYU Langone Health’s Epic electronic health record system, the organizations announced on 20 October 2026. The integration brings what the companies call patient-aware clinical intelligence to about 12.4 million outpatient visits and more than 421,000 emergency department visits each year across seven inpatient locations and more than 400 outpatient sites in New York and Florida.

Clinicians across NYU Langone, one of the nation’s premier academic health systems and ranked No. 1 for quality by Vizient Inc., will be able to ask complex clinical questions in natural language and receive answers grounded in peer-reviewed medical literature with patient context, all without leaving their Epic workflow. The deployment extends across NYU Langone’s hospitals, its ambulatory network, and the Family Health Centers at NYU Langone, one of the largest Federally Qualified Health Center networks in the nation, serving more than 100,000 patients through some 600,000 visits a year in Brooklyn and beyond.

i10X Quick Take

Quick Take

  1. What happened: OpenEvidence integrated into NYU Langone’s Epic EHR on 20 October 2026.
  2. Scale: The deployment reaches 12.4 million outpatient visits and 421,000 emergency visits annually.
  3. Reach: More than 6,000 physicians, 2,000 residents and fellows, and 54,000 employees will have access.
  4. Function: Clinicians can ask clinical questions in natural language and receive literature-grounded answers with patient context.
  5. Scope: The integration covers hospitals, ambulatory sites, Family Health Centers, and two medical schools.

In plain English

NYU Langone Health is putting an AI assistant directly into the electronic health record system its doctors use every day. When a physician has a clinical question, they can type it in natural language and get an answer based on peer-reviewed medical research, tailored to the specific patient they’re treating. The system doesn’t require doctors to leave the chart or switch to another application. NYU Langone handles about 12 million outpatient visits a year, making this one of the largest deployments of AI clinical decision support inside an Epic workflow. The goal is to bring the latest medical evidence to the point of care, where decisions happen.

What happened

On 20 October 2026, NYU Langone Health and OpenEvidence announced a collaboration to embed OpenEvidence directly into NYU Langone’s Epic electronic health record system. The integration delivers what the organizations call patient-aware clinical intelligence, meaning clinicians can ask complex clinical questions in natural language and receive answers that are grounded in peer-reviewed medical literature and informed by the patient’s chart, all without leaving the Epic workflow.

NYU Langone cares for patients during 12.4 million outpatient visits and more than 421,000 emergency department visits each year across seven inpatient locations and more than 400 outpatient locations in the New York region and Florida. The system’s 6,000-plus physicians and faculty, 2,000-plus residents and fellows, and over 54,000 employees make it one of the largest sources of care in the most populous metropolitan area in the United States. The deployment extends across NYU Langone’s hospitals, its ambulatory network, the Family Health Centers at NYU Langone (which serve more than 100,000 patients through some 600,000 visits a year in Brooklyn and beyond), and reaches the next generation of physicians training at NYU Grossman School of Medicine and NYU Grossman Long Island School of Medicine.

“At NYU Langone, we are committed to working with OpenEvidence to make the latest technology available to our clinicians in a safe and practical environment at scale,” said Nader Mherabi, executive vice president and vice dean, chief digital and information officer at NYU Langone Health, in the announcement.

Daniel Nadler, founder and CEO of OpenEvidence, said in the same release, “NYU Langone cares for New Yorkers at a scale few institutions in the country can match, and it does so while setting the standard of care across specialties. New York has always been where American medicine goes to prove itself at scale. Putting OpenEvidence inside the chart at NYU Langone means the world’s medical literature is now in the room for every one of the 12 million visits this system supports each year.”

The integration

The OpenEvidence integration sits inside Epic, the electronic health record system used by NYU Langone. Clinicians can ask clinical questions in natural language, the same way they might phrase a question to a colleague, and receive answers that are sourced and cited from peer-reviewed medical literature. The system is designed to incorporate patient context from the chart, meaning the answers are tailored to the specific patient the clinician is treating at that moment.

This approach differs from standalone AI tools that require clinicians to leave the EHR, open a separate application, and manually input patient details. By embedding the tool directly in the Epic workflow, NYU Langone aims to reduce friction and make evidence-based answers available at the point of care. The integration follows a pattern seen in other recent health AI deployments, including ChatGPT for Healthcare’s connection to Epic records and Microsoft Copilot Health’s platform strategy, where the goal is to meet clinicians where they already work rather than asking them to adopt new standalone tools.

According to OpenEvidence’s own materials, the platform is the most popular AI for doctors in the United States, with independent studies showing more American physicians use OpenEvidence than all other AI platforms combined. The company says it is trusted by millions of verified U.S. healthcare professionals making high-stakes clinical decisions at the point of care. OpenEvidence is free for all verified U.S. clinicians.

Why it matters

The NYU Langone deployment is significant for three reasons: scale, workflow integration, and the patient-aware design. At 12 million visits a year, this is one of the largest known integrations of AI clinical decision support inside an Epic EHR. The workflow integration means clinicians don’t have to leave the chart, which is critical for adoption in high-volume settings where every second counts. The patient-aware design, which tailors answers to the specific patient in the chart, moves beyond generic literature search toward contextualized clinical intelligence.

The deployment also reaches medical trainees at two medical schools, meaning the next generation of physicians will learn to practice with AI-assisted evidence retrieval as a standard part of their workflow. This could shape expectations and habits for years to come.

NYU Langone’s ranking as No. 1 for quality by Vizient Inc. and its status as one of the nation’s premier academic health systems give the deployment credibility. If the integration proves effective at NYU Langone, other large academic medical centers and health systems may follow. The announcement does not include performance metrics, adoption rates, or clinician satisfaction data, so the real-world impact remains to be measured.

What’s still open

  • How many clinicians at NYU Langone are actively using the OpenEvidence integration, and how often?
  • What specific clinical questions are being asked, and in which specialties is adoption highest?
  • Does the integration reduce time spent searching for evidence, and does it change clinical decisions?
  • How does NYU Langone measure the accuracy and safety of the AI-generated answers, and what oversight is in place?
  • Will OpenEvidence share performance data or publish peer-reviewed studies on the deployment’s impact?

About the analysis

Researched and written with AI assistance under the editorial responsibility of the i10X News team. The title image is an AI-generated image. Read our AI Use Policy. Spotted an error? Request a correction.

This independent i10x analysis is based on NYU Langone’s partnership announcement and OpenEvidence’s own product announcement. Source names are given in the text; we do not link out to those pages.

i10x Perspective

The NYU Langone deployment is a test of whether AI clinical decision support can work at scale inside the EHR, where clinicians actually practice. The patient-aware design is the right approach, but the proof will be in adoption rates and whether the tool changes clinical decisions in ways that improve outcomes. The announcement is heavy on scale and light on evidence of impact. If OpenEvidence and NYU Langone publish real-world performance data, including clinician satisfaction, time savings, and decision quality, this deployment could set a standard for AI in clinical workflows. Without that data, it remains a promising experiment.

The integration also raises questions about oversight and liability. When an AI tool sits inside the EHR and provides patient-specific clinical guidance, who is responsible if the answer is wrong? The American Medical Association’s recent policy statement that AI cannot be licensed to practice medicine underscores the need for clear physician oversight and liability protections. NYU Langone and OpenEvidence will need to demonstrate not just that the tool is useful, but that it is safe and that accountability is clear.

Christopher Ort

Christopher Ort

Christopher Ort handles SEO, AI agent workflows and PR & partnerships at i10x.ai, the all-in-one AI workspace built by i10X Global Pte. Ltd. in Singapore. He is a graduate of Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU). He is the author of “The Style Penalty”, a study published on SSRN that analyses 1,576 evaluation decisions by four frontier AI models to show how AI-written CVs fare in automated hiring screens; the research has been covered by heise online and t3n.

Editor's picks

  1. CVE-2026-129877: DeepAudit exposes LLM API keys and Git tokens to unauthenticated attackers
  2. CVE-2026-129875: REBUILD 4.5.0–4.5.4 password hash disclosure via MCP QueryRecords
  3. South Korea Weighs Nuclear Power to Meet AI Electricity Demand
  4. UK and US Partner to Accelerate Nuclear Fusion with AI
  5. Texas and New Mexico Data Center Emissions Rise With AI Buildout