Palo Alto, Calif.-based Stanford Health Care has developed AI to message patients with test results and answer billing questions.
After becoming an early adopter of an Epic and Microsoft program to draft general patient portal messages with AI, Stanford designed software to do the same for test and lab result notifications and answers to billing queries.
More than 50% of providers have been going with the draft messages for test results, compared to about 17-20% for the general patient portal message project. The health system plans to publish research with more quantitative and qualitative data soon.
“It’s a really sophisticated tool that can span different encounters, look at trends, look at different kinds of results,” Michael Pfeffer, MD, senior vice president and chief information and digital officer of Stanford Health Care, told Becker’s. “It’s really incredible.”
In the earlier project, providers reported less cognitive burden and lower perceived burnout.
Stanford used AI company Anthropic’s Claude large language model to develop the solutions and meld them into existing workflows, through the health system’s Epic EHR.
“One of the most important learning points is that embedding it into the workflow is absolutely critical,” Dr. Pfeffer said. “It couldn’t be that clinicians had to move into a different tool in order to do this and move back into the electronic health record. So that usability aspect of it was really powerful.”
Dr. Pfeffer said he doesn’t know of any existing solutions in the market for test results and billing questions.
“We want to continue to learn how to do this, because there are so many opportunities for automation and using AI and the models that are available,” he said. “Rather than buying a point solution for every particular use case, we are leveraging our platform capabilities, as well as current tools like our electronic health record.”
Dr. Pfeffer believes the technology will enable future opportunities, such as real-time reporting and looking deeper into the medical record for clinical insights.
“It’s really exciting, and we’re just scratching the surface right now of the potential of embedding AI into all the different workflows,” he said.
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.