Healthcare organizations require AI that operates across the systems and information central to care and operations. Patient context, medical evidence, public healthcare data, and organizational knowledge frequently reside in separate locations. Bringing these sources together in a governed workspace helps teams locate the right information, interpret it in context, and apply it across their business.
OpenAI is introducing a new electronic health record integration that brings authorized patient context from Epic into ChatGPT for Healthcare, alongside a Healthcare Public Data plugin offering direct, structured access to official healthcare datasets such as PubMed, DailyMed, and CMS Coverage. Together, these capabilities move ChatGPT closer to the systems and sources healthcare teams depend on, while maintaining the controls and compliance healthcare work demands.
Connecting ChatGPT with EHR Context
Healthcare organizations can now link Epic environments to ChatGPT. Rather than searching through appointment notes, lab results, medications, and specialist documentation separately, clinicians can ask questions like:
- What has changed since this patient's last visit?
- Which recent lab results should be reviewed before today's appointment?
- Have there been medication changes or new specialist recommendations?
- What follow-ups, referrals, or unresolved issues require attention?
ChatGPT consolidates relevant information from the authorized patient record, summarizes key developments, and references supporting chart data.
The integration supports two complementary experiences:
- EHR context in ChatGPT: Authorized patient information from a supported EHR can be brought into ChatGPT to review patient history, identify changes, and prepare for appointments.
- ChatGPT in the EHR workflow: In supported deployments, ChatGPT can be embedded directly into an EHR layout, enabling AI-assisted workflows without leaving the patient chart.
Suresh Gunasekaran, President and CEO of UCSF Health, noted that as a pilot partner they are exploring how the new EHR integration can help clinical teams understand what has changed and what matters most across complex patient records, potentially reducing time spent synthesizing data and giving clinicians more time with patients.
These experiences are designed to complement existing EHR workflows, helping clinicians review authorized patient information alongside other trusted sources in ChatGPT.
Nine Official Healthcare Sources Through One Plugin
Patient context is only one part of the information healthcare teams rely on. They also draw on current research and official data about medications, coverage, clinical trials, and providers.
ChatGPT for Healthcare already assists teams in answering clinical questions and synthesizing medical research through trusted clinical search across thousands of medical sources. Expanding on that foundation, the Healthcare Public Data plugin unifies dedicated connectors to nine official public healthcare sources, including ClinicalTrials.gov, CMS Coverage, RxNorm, DailyMed, and PubMed. Teams can work with specific records, fields, identifiers, and versions while focusing on these authoritative sources. This simplifies comparing and verifying precise information-such as trial eligibility criteria, medication identifiers, coverage policy versions, and provider records-without searching each source individually.
For example, a research team could use ClinicalTrials.gov to identify actively recruiting trials and compare eligibility criteria, while a pharmacy team could use DailyMed to confirm the latest label and warnings for a medication. A population health team planning a diabetes-prevention program could combine relevant research, active trials, and Medicare coverage information in a source-backed view to help program leaders evaluate options and identify open questions.
Validated Through Real Healthcare Scenarios
Effectively using connected healthcare context depends on models that can interpret it accurately. OpenAI collaborates with hundreds of physicians across 60 countries, 49 languages, and 26 medical specialties to define, measure, and improve health responses in ChatGPT. To date, these physicians have reviewed over 700,000 model responses across examples reflecting real-world healthcare questions, with their feedback improving model behavior and strengthening healthcare-specific tools.
To assess ChatGPT's performance with connected EHR context, physicians evaluated responses across 27 clinical use cases, including pre-visit review, clinical timelines, medication review, and handoff summaries. Across 4,363 ratings, physicians rated 99.1% of responses safe across all use cases.
In a separate two-round evaluation, physicians reviewed hundreds of ChatGPT responses to nuanced clinical questions based on large U.S. healthcare datasets. For each of the five connected data sources tested, more than 93% of responses received a rating of "good" or better accuracy.
These evaluations measure how ChatGPT works with healthcare context-from surfacing relevant information to citing supporting evidence and preparing work for clinician and staff review. OpenAI continues to invest in dedicated training and evaluation for healthcare to further improve ChatGPT's performance and reliability.
Applying Healthcare and Business Information
The same governed workspace that helps teams find and understand healthcare information can also help them apply it across research, operations, business, and technology. Clinical and business teams can use ChatGPT Work to transform information into reports, analyses, presentations, and plans for review. Technical teams can use Codex to build and improve software supporting care delivery and business operations.
Plugins for Microsoft SharePoint, Google Drive, Salesforce, Slack, and other enterprise systems expand the approved business context available in ChatGPT while preserving existing permissions.
Robert Purinton, Chief AI Officer at AdventHealth, commented that by equipping team members with tools like ChatGPT Work, Codex, and connected business data, AI can reduce routine work and accelerate practical innovations, giving caregivers and teams more time for human connection.
Getting Started with ChatGPT for Healthcare
ChatGPT for Healthcare provides clinical, research, and administrative teams a governed workspace for AI use. It combines healthcare-specific capabilities with enterprise controls including role-based access, single sign-on, and audit logs. With an applicable Business Associate Agreement, customers can use ChatGPT Work, Codex, apps, and plugins within the same workspace to support HIPAA-compliant workflows.
- ChatGPT for Healthcare customers: Workspace administrators can enable the EHR integration and Healthcare Public Data plugin.
- ChatGPT Enterprise customers: Contact the OpenAI account team to confirm eligibility and determine the right configuration for a Regulated Workspace.
- Individual clinicians: Eligible U.S. ChatGPT for Clinicians users can install the Healthcare Public Data plugin. The EHR integration is not available for individual accounts.
Healthcare organizations can begin with the capabilities that fit their needs and expand over time, bringing more of the information central to care and operations into one governed workspace.
Launch partners include AdventHealth, Baylor Scott & White Health, Boston Children's Hospital, Cedars-Sinai, HCA Healthcare, Memorial Sloan Kettering Cancer Center, and UCSF.