OpenAI Connects Epic Health Records and Public Data to ChatGPT

OpenAI said on September 1, 2026 that healthcare organizations can now connect their Epic electronic health record environments to ChatGPT for Healthcare, alongside a new Healthcare Public Data plugin that links the workspace to nine official healthcare datasets.

The announcement, published on OpenAI’s newsroom, describes two complementary capabilities. The EHR integration brings authorized patient context from Epic into ChatGPT, while the public data plugin gives teams structured access to sources including PubMed, DailyMed, and CMS Coverage.

Epic EHR Integration

Under the integration, clinicians can ask ChatGPT questions grounded in a patient’s authorized record rather than searching across appointment notes, laboratory results, medications, and specialist documentation. OpenAI said clinicians can use the tool to review patient history, identify changes since a prior visit, and prepare for appointments.

The company described the integration as supporting two experiences. In the first, authorized patient information from a supported EHR is brought into ChatGPT. In the second, available in supported deployments, ChatGPT is embedded directly into an EHR layout so clinicians can use AI-assisted workflows without leaving the patient chart.

OpenAI said the integration is designed to complement existing EHR workflows. The company said Epic’s system holds data for a large patient population, and that the integration allows read-only access to records, with the AI not writing anything back to the chart.

Suresh Gunasekaran, president and CEO of UCSF Health, described his organization as a pilot partner. “As a pilot partner, we’re exploring how the new EHR integration with ChatGPT for Healthcare can help clinical teams understand what has changed and what matters most across a complex patient record,” he said in the announcement. “By bringing relevant information together more quickly and comprehensively, the technology has the potential to reduce time spent synthesizing data and give clinicians more time with patients.”

Healthcare Public Data Plugin

The second capability, the Healthcare Public Data plugin, consolidates connectors to nine official public healthcare sources, including ClinicalTrials.gov, CMS Coverage, RxNorm, DailyMed, and PubMed. OpenAI said teams can work with specific records, fields, identifiers, and versions while focusing queries on these authoritative sources.

The company said the plugin is intended to make 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. OpenAI described example uses: a research team could use ClinicalTrials.gov to identify actively recruiting trials and compare eligibility criteria, a pharmacy team could use DailyMed to confirm the latest label and warnings for a medication, and a population health team could bring research, active trials, and Medicare coverage information together for a diabetes-prevention program.

Physician Evaluation Results

OpenAI said it partners with hundreds of physicians across 60 countries, 49 languages, and 26 medical specialties to define and measure health responses in ChatGPT. The company said these physicians have reviewed more than 700,000 model responses to date.

To assess performance with connected EHR context, OpenAI said 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 as safe across all use cases, the company reported.

In a separate two-round evaluation, OpenAI said physicians reviewed hundreds of ChatGPT responses to 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, according to the company.

These figures are OpenAI’s own reported evaluation results.

Access and Compliance

OpenAI said ChatGPT for Healthcare 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 in the same workspace to support HIPAA-compliant workflows. Plugins for Microsoft SharePoint, Google Drive, Salesforce, Slack, and other enterprise systems expand the available business context while preserving existing permissions.

On availability, OpenAI said ChatGPT for Healthcare customers should ask their workspace administrator to enable the EHR integration and Healthcare Public Data plugin. ChatGPT Enterprise customers were directed to contact their OpenAI account team to confirm eligibility and configuration for a Regulated Workspace. The company said eligible U.S. ChatGPT for Clinicians users can install the Healthcare Public Data plugin, but that the EHR integration is not available for individual accounts.

OpenAI listed AdventHealth, Baylor Scott & White Health, Boston Children’s Hospital, Cedars-Sinai, HCA Healthcare, Memorial Sloan Kettering Cancer Center, and UCSF as healthcare launch partners for the product.