ChatGPT for Healthcare can now connect directly to Epic electronic health record environments and offers a Healthcare Public Data plugin that provides structured access to official health data sources such as PubMed, DailyMed, and CMS Coverage.
Why this matters
Patient context, clinical evidence, public health datasets and organizational knowledge often live in separate systems. A governed workspace that connects these sources helps teams locate relevant information, understand it in context, and use it safely across clinical, research and operational tasks.
Epic integration: authorized patient context in one place
Organizations can link Epic environments to ChatGPT for Healthcare so clinicians no longer need to search multiple records separately — appointment notes, lab results, medication lists and specialist documentation can be reviewed together. ChatGPT aggregates relevant items from the authorized patient record, summarizes key developments and points back to supporting chart data.
The integration supports two complementary experiences designed to fit alongside existing EHR workflows and allow clinicians to review authorized patient information together with other trusted sources inside ChatGPT.
Healthcare Public Data plugin: structured access to official sources
The Healthcare Public Data plugin provides dedicated connectors to nine official public health datasets, including ClinicalTrials.gov, CMS Coverage, RxNorm, DailyMed and PubMed. Teams can work with specific records, fields, identifiers and versions, making it easier to compare and verify precise information — such as trial eligibility criteria, medication identifiers, coverage policy versions and provider records — without searching each source separately.
Practical examples
- A research team could use ClinicalTrials.gov to identify actively recruiting trials and compare eligibility criteria.
- A pharmacy team could consult DailyMed to confirm the latest label and warnings for a medication.
- A population health group planning a diabetes-prevention program could assemble relevant research, active trials and Medicare coverage data into a source-backed view for program evaluation.
Modeling, clinical collaboration and evaluations
OpenAI states that clinical expertise is central to accurate model behavior. Hundreds of physicians across 60 countries, 49 languages and 26 medical specialties have collaborated with OpenAI; to date they have reviewed more than 700,000 model responses across real-world healthcare examples.
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 judged 99.1% of responses safe for the tested 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 were rated as having “good” or better accuracy.
These evaluations measure how ChatGPT surfaces relevant information, cites supporting evidence and prepares work products that clinicians and staff can review. OpenAI says it continues to invest in domain-specific training and evaluation to further improve performance and reliability in healthcare contexts.
Governance, enterprise controls and workspace
ChatGPT for Healthcare provides a governed workspace for clinical, research and administrative teams and pairs healthcare-specific features with enterprise controls such as role-based access, single sign-on and audit logs. With an applicable Business Associate Agreement (BAA), customers can use ChatGPT Work, Codex, apps and plugins in the same workspace to support HIPAA-compliant workflows.
The platform also supports plugins for enterprise systems including Microsoft SharePoint, Google Drive, Salesforce and Slack, expanding approved business context in ChatGPT while preserving existing permissions.
How organizations can proceed
Healthcare organizations can adopt the capabilities that match their needs and expand over time, bringing more of the information central to care and operations into a single governed workspace.
Contact
Interested organizations are invited to contact OpenAI’s sales team to find a suitable solution for their environment.
