OpenAI and Epic Systems have announced a new integration that allows healthcare professionals to use ChatGPT to directly query electronic health records, marking a notable advancement in how clinical teams access and synthesize patient data.
This integration reduces the difficulties healthcare providers face when accessing patient information before and during interactions, by enabling clinicians to query patient-specific information directly within the AI environment.
Clinicians can use this integration to identify which screenings a patient is due for or determine which lab results to review ahead of an appointment, making it a useful tool for care.
According to the announcement, the core challenge the partnership seeks to address is the need for AI that works across the systems and information central to care and operations, as patient context, medical evidence, public healthcare data, and organizational knowledge often live in different places.
OpenAI stated that connecting these sources in a governed workspace helps teams find the right information, understand it in context, and put it to work across the business, and they achieved this by developing the ChatGPT EHR integration.
The integration allows clinicians to access AI capabilities without leaving the patient chart, enabling them to make more informed decisions and provide better care, as they can quickly access relevant information.
UCSF Health served as a pilot partner on the project, giving the integration a real-world clinical testing ground, and Suresh Gunasekaran, president and CEO of UCSF Health, commented on the technology’s potential.
Suresh Gunasekaran said that it has the potential to reduce time spent synthesizing data and give clinicians more time with patients, which could lead to better patient outcomes.
The Healthcare Public Data plugin is a focused expansion of ChatGPT’s capabilities within clinical and research environments, directing the AI to pull responses from nine verified public health resources.
Related: Siemens Healthineers wins $31M federal grant for stroke robotics
These resources include ClinicalTrials.gov, the CMS Coverage Database, and PubMed, and the plugin builds on ChatGPT’s existing ability to help teams answer clinical questions and synthesize medical research.
It anchors responses in official, publicly available data, allowing research teams to identify trials in active recruitment and pharmacists to consult the most recent medication warnings, making it a valuable tool for clinical decision-making.
Teams performing multidisciplinary work, such as population health teams, can query all nine sources simultaneously, and they can use this plugin to inform their decisions.
OpenAI emphasized the safety and accuracy standards behind the ChatGPT EHR integration, noting that they worked alongside physician partners to evaluate the connected EHR context across 27 clinical use cases.
Across a total of 4,363 ratings, physicians rated 99.1% of ChatGPT responses as safe across all use cases, and 93% of tested responses were rated as having “good” or better accuracy, demonstrating the integration’s potential.
The integration of ChatGPT into EHR workflows has the potential to significantly impact the way clinicians work, by providing them with quick access to relevant information and reducing the time spent on data synthesis.
This could lead to better patient outcomes and more efficient care, as clinicians can focus on patient interactions rather than data synthesis, and the dual release of the Epic Systems integration and the Healthcare Public Data plugin positions ChatGPT as a more structured and verifiable resource for clinical teams.
They are supported by real-world pilot data and direct integration into established healthcare workflows, making ChatGPT a useful tool for clinician productivity.
