ChatGPT Health to integrate with Epic, letting clinicians import patient records
OpenAI is integrating ChatGPT Health with Epic's electronic health record system, allowing clinicians to import and analyze patient data with AI. The company stresses access is read-only and that AI remains unsuitable for diagnosis or treatment.
OpenAI has announced that ChatGPT Health will integrate with Epic, the electronic health record (EHR) system that holds data for more than 325 million patients. In certain systems, ChatGPT will be built directly into EHR workflows, letting clinicians use it without leaving a patient's chart.
With the integration, clinicians will be able to access and summarize information such as appointment notes, lab results, medication lists, and specialist documentation. The tool also allows reviewing patient history, spotting changes over time, and preparing for upcoming appointments. In some deployments, clinicians will be able to use ChatGPT for pre-visit reviews and to build clinical timelines directly from within the chart.
OpenAI emphasized that the integration provides only read-only access to health records — the AI does not write anything back into the system. The company is also introducing a new Healthcare Public Data plugin that pulls information from sources including ClinicalTrials.gov, CMS Coverage, RxNorm, DailyMed, and PubMed. This is meant to help healthcare workers synthesize data on clinical trial eligibility, medication identifiers, and insurance coverage policies.
Organizations with a Business Associate Agreement in place will also be able to use ChatGPT Work, Codex, apps, and connectors within compliant workflows.
Last month, OpenAI rolled out ChatGPT's health features to all U.S. consumers, noting that users send about 300 million health-related queries per week. The company continues to maintain that AI is not suitable for diagnosis or treatment. In testing that gathered over 4,300 physician responses across 27 clinical use cases, 99.1% of responses were found to be safe.
Still, even a small share of unsafe answers can cause serious harm. OpenAI was recently sued by a Florida-based pastor who alleged ChatGPT gave him a near-fatal recommendation. In May, the company was also sued by family members of another user who blamed ChatGPT for wrongful advice related to medication dosage.
