Tools

AI-generated text

OpenAI integrates ChatGPT Health with Epic EHR to give clinicians read-only access to patient records

OpenAI has integrated ChatGPT Health with Epic’s electronic health record system, which holds data for more than 325 million patients, allowing clinicians to import and query patient information and—where available—use ChatGPT inside EHR workflows.

OpenAI integrates ChatGPT Health with Epic EHR to give clinicians read-only access to patient records

OpenAI announced that it has integrated ChatGPT Health with Epic’s electronic health record (EHR) system, which contains records for more than 325 million patients. The integration lets clinicians import patient data into ChatGPT and query it with AI-assisted prompts to produce summaries and timelines.

What clinicians can do

According to the company, clinicians can use ChatGPT to access and summarize appointment notes, laboratory results, medications, and specialist documentation. They can review patient histories to identify changes and prepare for upcoming visits. In some deployments, ChatGPT is embedded directly into EHR workflows so clinicians can request pre-visit reviews and build clinical timelines without leaving a patient chart.

OpenAI emphasized that the integration provides read-only access to health records; the AI does not write back to the medical record.

Healthcare Public Data plugin

OpenAI is launching a Healthcare Public Data plugin that can fetch information from public sources including ClinicalTrials.gov, CMS Coverage, RxNorm, DailyMed, and PubMed. The company says the plugin can help healthcare workers synthesize data for trial eligibility criteria, medication identifiers, coverage policy versions, and provider records.

Compliance and enterprise features

OpenAI said organizations that have a Business Associate Agreement (BAA) can enable ChatGPT Work, Codex, apps, and connectors in their workspace to support compliant workflows.

Usage numbers and safety findings

Last month, OpenAI rolled out ChatGPT for health to all U.S. consumers; the company previously said people ask about 300 million health-related questions on ChatGPT weekly. OpenAI also reported collecting more than 4,300 responses from physicians across 27 clinical use cases — including pre-visit review, clinical timelines, medication review, and handoff summaries — and found that 99.1% of those responses were safe. The company noted, however, that even a small number of unsafe answers can have harmful consequences for patients.

Legal challenges

Days before this rollout, a Florida-based pastor sued OpenAI alleging that ChatGPT gave him a near-fatal recommendation. Separately, in May the company was sued by family members of a user who said ChatGPT provided wrongful dosing advice.

Why this matters

By connecting to Epic’s EHR, ChatGPT Health can become a more practical tool for clinicians to process information and prepare for visits. The integration’s read-only restriction, the company’s internal safety evaluations, and ongoing legal challenges underscore persistent concerns about the limits of AI in clinical decision-making and the need for continued oversight and safeguards.