OpenAI today announced that it will integrate ChatGPT Health with Epic’s electronic health record (EHR) system, which holds data on more than 325 million patients, allowing clinicians to import patient data and ask questions using AI. The company said certain systems will integrate ChatGPT directly within EHR workflows.
ChatGPT allows clinicians to access and easily summarize information such as appointment notes, test results, medications, and professional documentation. You can also review a patient’s medical history, identify changes, and prepare for future visits. OpenAI says that in some implementations, clinicians can access ChatGPT directly to obtain pre-visit reviews and build clinical timelines without leaving the patient’s medical record. The company specified that the integration would only allow read-only access to medical records and that the AI would not write anything back.
OpenAI is also adding a new Healthcare Public Data plugin that can pull information from sources such as ClinicalTrials.gov, CMS Coverage, RxNorm, DailyMed, and PubMed. The company said the new plugin helps healthcare providers integrate data such as trial eligibility criteria, drug identifiers, coverage insurance versions, and provider records.
Separately from enabling these new features, the company said it will also enable organizations with business collaboration agreements to use ChatGPT Work, Codex, apps and connectors in their workspaces for compliant workflows.
Last month, OpenAI rolled out ChatGPT for Health to all U.S. consumers. The company announced at the time that people make 300 million health-related queries to ChatGPT every week. Despite many tight integrations with medical systems, the company has argued that AI is not suitable for diagnosis or treatment.
OpenAI said it collected more than 4,300 responses from physicians across 27 clinical use cases, including pre-visit reviews, clinical timelines, medication reviews, and handoff summaries, and found 99.1% of responses to be safe. However, any unsafe answer can lead to harmful consequences for humans.
Days before this development, a Florida-based pastor sued the company, claiming that ChatGPT gave him deadly advice. The company was also sued in May by the family of a user who accused ChatGPT of giving inappropriate dosage advice.
If you buy through links in our articles, we may earn a small commission. This does not affect editorial independence.
