Vanderbilt University Medical Center announced this past week that it's begun piloting an artificial intelligence tool from Nuance to help its physicians with clinical documentation.

WHY IT MATTERS
VUMC says it has enlisted 10 physicians to use and assess Nuance's DAX Copilot system, which can help automate the creation of clinical notes and reduce the administrative burden of charting in the electronic health record.

By listening to physician-patient encounters the natural language processing technology uses generative AI to generate real-time clinic visit notes with appropriate headings and context, according to VUMC, which are then able to be reviewed and edited by doctors before being integrated directly into the Epic EHR system.

Physicians from the VUMC's Division of General Internal Medicine and Public Health and Department of Orthopaedic Surgery, will test the Nuance first. But the health system may 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 in-house version of OpenAI’s large language model, which is deployed inside of VUMC’s Azure cloud tenant and is available to clinicians, who can experiment using this interface as an alternative to the public version of ChatGPT – which is disabled on VUMC’s networks for privacy considerations.

This offers more controls than the public chat interface from OpenAI, with VUMC retaining control over all data submitted to the HIPAA tool, which is certified and its use is covered under VUMC’s Business Associates Agreement with Microsoft.

“Health IT worked closely with leaders in the Department of Biomedical Informatics 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 LARGER TREND
VUMC has deep experience with clinical AI tools, including the in-house developing of some of its own. Ten years ago, for instance, biomedical informaticists there developed an automated application to predict elective surgical case volume – offering an advance look at case volumes that enables nursing and anesthesia managers to fine-tune staffing levels more proactively.

The Vanderbilt-Ingram Cancer Center was an early adopter of using AI to help schedule treatment for patients with cancer, the health system points out, using an automation tool to help reduce patient wait times at infusion centers, help with nurse scheduling, and improve throughput.

Other recent AI explorations at Vanderbilt include funding from the Gordon and Betty Moore Foundation to help it work with the Coalition for Health AI and the University of Iowa to develop a model framework and improve oversight of AI technology by health systems. Also, VUMC has explored using AI and Smart on FHIR in voice assistant, and creation of natural language processing voice assistant for its Epic EHR.

WHY IT MATTERS

ON THE RECORD
"This continues VUMC’s commitment to identifying and integrating leading health care technologies for quality, safety, and an enhanced patient/provider experience," said Mize of the DAX Copilot initiative, in a statement.

"Generative AI shows promise in improving both the quality and efficiency of health care documentation. The upcoming pilot marks a significant step in VUMC’s exploration of AI’s potential in streamlining clinician workflows and enhancing medical record-keeping while reducing time spent on documentation."

Mike Miliard is executive editor of Healthcare IT News
Email the writer: mike.miliard@himssmedia.com
Healthcare IT News is a HIMSS publication.