Skip to main content

Hospitals Are Using AI to Answer Some Patient Queries

Analysis  |  By Eric Wicklund  
   May 31, 2023

Four health systems are testing out a generative AI tool through the Epic EHR platform that provides answers to commonly asked and time-sensitive e-mails sent by patients to their doctors.

Four health systems across the country are piloting a generative AI tool within their Epic EHR platform to generate answers to certain patient messages.

The project aims to reduce workload stress for clinicians, particularly during their off hours, by sorting through their e-mail in-box and providing answers to commonly asked and time-sensitive questions. The answers are reviewed by the clinician before they're sent to the patient.

North Carolina's UNC Health, UC San Diego Health, Wisconsin-based UW Health, and Stanford Health Care are taking part in the project, along with Epic and Microsoft. A small number of physicians from each health system will be testing the tool, which runs on Epic's EHR and Microsoft's Azure cloud platforms.

“A good use of technology simplifies things related to workforce and workflow,” Chero Goswami, chief information officer at UW Health, said in an April press release from Microsoft announcing the project. “Integrating generative AI into some of our daily workflows will increase productivity for many of our providers, allowing them to focus on the clinical duties that truly require their attention.”

“We are incredibly excited that UNC Health’s work to build strong foundational IT systems and our existing use of AI tools has established us as a national leader helping drive the future of AI in healthcare,” Brent Lamm, UNC Health’s SVP and chief information officer, said in a separate release put out by the health system last week. “For us, the goal is to find ways we can thoughtfully and safely use AI to improve our teammates’ experience and help them focus on patients.”

According to UNC officials, who rolled out the tool to between five and 10 physicians, the project began with "a small subset of more administrative-type messages, similar to how your phone can suggest responses to texts." The answers aren't designed to replace a clinician's judgment, but rather save that clinician the time and effort involved in reading multiple e-mails.

The platform also incorporates natural language processing.

“Our exploration of OpenAI’s GPT-4 has shown the potential to increase the power and accessibility of self-service reporting through (Epic's self-service reporting tool) SlicerDicer, making it easier for healthcare organizations to identify operational improvements, including ways to reduce costs and to find answers to questions locally and in a broader context,” Seth Hain, senior vice president of research and development at Epic, said in a press release.

Eric Wicklund is the associate content manager and senior editor for Innovation, Technology, and Pharma for HealthLeaders.


UNC Health, UW Health, UC San Diego Health, and Stanford Health Care are partnering with Epic and Microsoft on a pilot program designed to reduce workload stress for clinicians, particularly during off hours.

The project uses a generative AI tool to answer select e-mails from patients that contain commonly asked or time-sensitive queries, much like a smartphone can offer common responses to a text.

The answers are reviewed by the clinician before they are sent to the patient.

Get the latest on healthcare leadership in your inbox.