Thursday Sep 3
HEALTHOpenAI

ChatGPT Gets Into The Chart, One Way

1SEP
EPIC EHRCHATGPTREAD ONLY

OpenAI connected ChatGPT for Healthcare to Epic. Clinicians can now ask questions grounded in a patient's authorized record. Access is read-only, so nothing goes back into the chart.

Epic holds data on more than 325 million people. That is most of the US clinical history sitting behind one integration.

Two shapes ship. Either the authorized file flows in, or the assistant embeds inside the EHR layout so nobody leaves the workflow.

A public-data plugin also arrived, wired to nine official sources including ClinicalTrials.gov, CMS Coverage, RxNorm, DailyMed and PubMed. Physicians rated 99.1% of responses safe across 4,363 evaluations.

full brief & sources

⚡ Why this matters

  • This is the read side of the biggest clinical dataset in the country going live inside a consumer assistant brand.
  • Read-only is the whole design. It is also the ceiling on how much work this can actually take off a clinician.
  • The public-data plugin matters more than it looks. Grounding on ClinicalTrials.gov and RxNorm is what makes answers checkable.

🔍 What happened

  • Healthcare organizations can connect their Epic environments to ChatGPT for Healthcare, announced September 1.
  • Clinicians ask questions against a patient's authorized record instead of hunting across notes, labs, meds and specialist documentation.
  • Two deployment models: pull the record into ChatGPT, or embed ChatGPT inside the EHR layout.
  • Nothing is written back to the chart.
  • A separate Healthcare Public Data plugin links nine official datasets.

💬 Smart takes

  • OpenAI's own number: physicians rated 99.1% of responses safe across 4,363 evaluations. That is a safety rate, not an accuracy rate. The two are not the same.
  • Health IT coverage frames it as a distribution win more than a capability win. Epic is the moat everyone wants inside.
  • Clinician skeptics point out that reading is the easy half. Documentation burden lives on the write side, which this does not touch.

🧭 Where this goes

  1. Likelywrite-back arrives within a year, gated by specialty and note type. Read-only is a trust ramp, not a principle.
  2. PossibleEpic ships a competing native assistant and the integration narrows to a channel deal.
  3. Wild Carda high-profile misread triggers a regulator to ask whether a chat interface over a chart is a medical device.

🥄 The Spoon Take

Read-only is the product decision worth copying. OpenAI shipped the half that cannot hurt anyone and let trust compound before touching the record. Most teams do the opposite: full write access on day one, then a year of apologizing. Constraint as a launch strategy is underrated.

🤔 Pushback

Safe is not correct. A 99.1% safety score says nothing about how often the summary missed the thing that mattered.

·ChatGPT Health adds Epic integration for clinicians to import patient data (TechCrunch)·ChatGPT for Healthcare unveils new integrations with Epic, public health data sources (Fierce Healthcare)·ChatGPT for Healthcare adds Epic integration (Becker's Hospital Review)·OpenAI Brings Epic Health Records to ChatGPT for Clinicians (PYMNTS)