ChatGPT for Healthcare can now read a patient's Epic record

The chart a doctor reads before walking into the room can now be summarized by ChatGPT, straight from Epic.

The integration

On September 1, 2026 OpenAI added an electronic health record integration to ChatGPT for Healthcare. Healthcare organizations can connect their Epic environments so that clinicians can ask what has changed since a patient’s last visit, which recent lab results to review, whether medications or specialist recommendations changed, and what follow-ups are outstanding. ChatGPT pulls the relevant information from the authorized record, summarizes it and points back to the supporting chart entries. TechCrunch describes the access as read-only. The integration works both inside ChatGPT and, in supported deployments, inside the EHR layout itself.

A second addition, the Healthcare Public Data plugin, connects nine official sources including ClinicalTrials.gov, CMS Coverage, RxNorm, DailyMed and PubMed, so teams can check trial eligibility, medication labels and coverage policies against the record versions they need.

The evaluation

OpenAI says physicians evaluated responses across 27 clinical use cases, including pre-visit review, clinical timelines, medication review and handoff summaries, and rated 99.1% of 4,363 responses safe. UCSF Health is a pilot partner; its president and CEO said the organization is exploring how the integration can help clinical teams understand “what has changed and what matters most across a complex patient record.”

What it changes

The gap between a chatbot that knows medicine and a tool that knows this patient was the record. With Epic connected, ChatGPT for Healthcare closes it inside a governed workspace with role-based access, single sign-on and audit logs. The remaining 0.9% is where the scrutiny will go: in a clinic, a small error rate meets a large number of patients.