The virtual assistant for the VA
- By Matt Leonard
- Mar 09, 2017
A recently announced partnership aims to make it easier for veterans to schedule doctor appointments as part of the health care workflow.
Epic, the electronic health records firm working with the Department of Veterans Affairs on revamping its scheduling system, has partnered with Nuance to develop a voice-activated virtual assistant that makes it easier for veterans to schedule appointments. Those appointments are then integrated with their health records and the VA’s workflow.
Voice-driven workflows will be featured as part of the Medical Appointment Scheduling System program, a nationwide deployment of Epic scheduling software in VA Medical Centers, company officials said.
The technology behind the hands-free virtual assistant is called Florence -- a nod to Florence Nightingale -- which Nuance released a few years ago. The initial versions were designed for physician-facing applications – think of a doctor using voice commands to review a patent’s file or fill out different fields in a medication order.
“Basically it is a mechanism for a physician to have an intelligent, natural conversation with a system to accomplish some set of preconceived tasks,” said Joe Petro, Nuance’s senior vice president of healthcare research and development.
The process for making a test version for scheduling was relatively simple, he explained. The easiest tasks to set up for virtual assistants are ones that are very formulaic (easily modeled) and often repeated. Medication orders and scheduling meet both criteria.
With a simple user interface powered by artificial intelligence, the technology makes it easy to support intuitive voice-driven interactions. The Florence scheduling application guides patients through picking their doctor and shows them openings in that doctor’s schedule. The voice-driven process makes scheduling appointments easier for people with impaired vision or poor motor skills.
This would not be the first time the VA has tapped AI technology to help improve efficiency. The agency began working with Flow Health last year to use machine learning to take aggregated and anonymized VA data and create a knowledge graph that health practitioners can use to better treat veterans. And a recent study by Dr. Jennifer Garvin with the VA in Salt Lake City, Utah, tested a natural language processing prototype that searches through unstructured information in case notes for data related to chronic heart failure.
AI can play a vital role in decreasing the burdens on physicians who are responsible for ever more administrative tasks. The desire to lessen this work combined with the public’s increased familiarity with virtual assistants like Siri and Alexa has shown that the market is ready for a medical-facing virtual assist, Petro said.
I really think this could be “the breakthrough year for the conversational AI,” he said.
Matt Leonard is a reporter/producer at GCN.
Before joining GCN, Leonard worked as a local reporter for The Smithfield Times in southeastern Virginia. In his time there he wrote about town council meetings, local crime and what to do if a beaver dam floods your back yard. Over the last few years, he has spent time at The Commonwealth Times, The Denver Post and WTVR-CBS 6. He is a graduate of Virginia Commonwealth University, where he received the faculty award for print and online journalism.
Leonard can be contacted at firstname.lastname@example.org or follow him on Twitter @Matt_Lnrd.
Click here for previous articles by Leonard.