Lebanon, N.H.-based Dartmouth Health has built AI to filter patient portal messages and respond to patients.
Clinicians from the health system worked with Dartmouth computer science researchers and a Geisel School of Medicine associate professor to develop PortalPal, which uses AI to triage incoming messages and generate follow-up questions to patients.
“We want to encourage patients to interact with us through the patient portal, but we get a lot of messages,” said Tim Burdick, MD, associate professor of community and family medicine at the Geisel School of Medicine, in a June 25 Dartmouth article. “How do we respond to those messages in a timely fashion, and make sure that we’re responding to those messages with the right priorities?”
The researchers deployed large language models to judge the urgency of messages using publicly accessible online medical Q&A forums. They also employed anonymized patient data to assess which elements from patients’ charts would be most relevant for crafting follow-up questions. Dartmouth Health physicians and nurses then helped validate and refine the models.
At the Becker's 11th Annual IT + Revenue Cycle Conference: The Future of AI & Digital Health, taking place September 14–17 in Chicago, healthcare executives and digital leaders from across the country will come together to explore how AI, interoperability, cybersecurity, and revenue cycle innovation are transforming care delivery, strengthening financial performance, and driving the next era of digital health. Apply for complimentary registration now.