Vanderbilt University Medical Center announced last week that it has begun testing an artificial intelligence tool from Nuance to help its physicians with clinical documentation.
WHY IT MATTERS
VUMC say it has engaged ten physicians to use and evaluate Nuance's DAX Copilot system, which can help automate clinical note-taking and reduce the administrative burden of charting in the electronic health record.
By listening to doctor-patient encounters, the natural language processing technology uses generative AI to generate real-time clinic visit notes with appropriate titles and context, which can then be reviewed and edited by doctors before being sent directly be integrated into the system. Epic EHR system.
Doctors from the Department of General Internal Medicine and Public Health and the Department of Orthopedic Surgery of the VUMC will be the first to test the Nuance. But the health care system could also evaluate additional AI-powered documentation assistants in other departments, said Dr. Dara Mize, chief medical information officer at VUMC.
Vanderbilt researchers have also created aiChat, an internal version of OpenAI's large language model that is deployed in VUMC's Azure cloud tenant and available to clinicians who can experiment with using this interface as an alternative to the public version of ChatGPT – which has been disabled on VUMC's networks due to privacy concerns.
This provides more control than OpenAI's public chat interface, with VUMC maintaining control over all data sent to the HIPAA tool, which is certified and its use covered by VUMC's Business Associates Agreement with Microsoft.
“Health IT worked closely with Biomedical Informatics leaders to create a platform for the VUMC community to safely explore large language models,” said Travis Osterman, DO, associate VP for research informatics and associate CMIO for VUMC, in a statement.
THE BIG TREND
VUMC has in-depth experience with clinical AI tools, including the internal development of some proprietary tools. For example, ten years ago, biomedical informatics scientists there developed an automated application to predict the number of elective surgical cases – providing advance insight into case volume, allowing nurses and anesthesia managers to more proactively adjust staffing levels.
And the Vanderbilt-Ingram Cancer Center was an early adopter of using AI to plan treatment for patients with cancer, the health care system points out, using an automation tool to help reduce patient wait times at infusion centers. in nurse scheduling and throughput.
Other recent AI explorations at Vanderbilt include funding from the Gordon and Betty Moore Foundation to help it collaborate with the Coalition for Health AI and the University of Iowa to develop a modeling framework and improve oversight of AI technology by healthcare systems . VUMC also explored the use of AI and Smart on FHIR in voice assistant, and the creation of a natural language processing voice assistant for its Epic EHR.
WHY IT MATTERS
ON THE RECORD
“This is a continuation of VUMC's commitment to identifying and integrating leading healthcare technologies for quality, safety and an improved patient/provider experience,” Mize of the DAX Copilot initiative said in a statement.
“Generative AI holds promise in improving both the quality and efficiency of healthcare documentation. The upcoming pilot marks an important step in VUMC's exploration of AI's potential in streamlining physician workflows and improving medical record keeping, while reducing time spent on documentation.”
Mike Miliard is editor-in-chief of Healthcare IT News
Email the writer: mike.miliard@himssmedia.com
Healthcare IT News is a HIMSS publication.