While future studies could further investigate the utility of Nuance's generative artificial intelligence voice-enabled documentation tool for clinician subgroups and alternative clinical implementations, researchers said that the general availability of Nuance's Dragon Ambient Experience copilot in Atrium Health's electronic health records did not reveal significant improvements in key metrics for the organization.

WHY IT MATTERS

Last year, Charlotte, North Carolina-based Atrium Health, which merged with and became Advocate Health in 2022, touted itself as the first U.S. health system to deploy AI-driven ambient clinical documentation to automate the creation of clinical documentation during patient visits. 

For the post-DAX implementation study, published in the New England Journal of Medicine AI, Atrium and Wake Forest University School of Medicine researchers evaluated outcomes for participating clinicians after the health system implemented Nuance’s DAX Copilot.

They initially enrolled 238 clinicians specializing in family medicine, internal medicine and general pediatrics from outpatient clinics in North Carolina and Georgia in five waves, between June and August 2023.

Those in the group testing DAX received a one-hour training and were set up with an account via their Epic EHRs.

The researchers evaluated outcomes related to the EHRs over 180 days, including time in EHR, work time outside of work, time-in-note, completed appointment rate, same-day closure rate and note length, and financial metrics, such as work relative value units per visit. 

The final analytic sample the researchers assessed included 112 clinicians in the software user group and 103 clinicians in the control, non-DAX user group, they said.

They found that three-fourths of "active DAX users" (84/112) transferred more than 25% of their DAX notes to Epic and approximately 60% of "high DAX users" (67/112) transferred more than 60% of their DAX notes to their EHRs.

After controlling for age, gender, provider type, years of practice and baseline outcome, the researchers said they found few "statistically significant differences" between DAX users and the control group – save note time.

"High DAX users had an overall decrease of around 7% in documentation hours compared with the control group," they said in their report.

"Exploratory results suggested that modest reductions in note time could result from using DAX at a high utilization level or deploying DAX to select clinician subgroups," they added.

Wake Forest University Health Sciences, a part of the university's medical school that serves as the academic core of Advocate Health, funded the study.

THE LARGER TREND

Many organizations expanded their use of DAX Copilot this past year, including Intermountain Health, Pennsylvania-based WellSpan Health and others. 

EHR vendors also formed partnerships to integrate the documentation pool in an effort to reduce clinician burnout. In January, Epic fully embedded the Nuance AI copilot and in March, Meditech Expanse EHR announced its integration.

Meanwhile, in October, Microsoft reported that, after a year of availability, DAX was seeing momentum, and highlighted that the AI tool was used in at least 50% of patient encounters at Northwestern Medicine in Chicago. The health system's clinicians spent an average of 24% less time drafting notes and increased the number of patients they could see by an average of 11.3, the tech giant said.

ON THE RECORD

"Taken as a whole, these findings suggest that AI-enabled documentation’s efficiencies may translate to decreased markers of burnout for a subset of clinicians, and perhaps more broadly when the implementation of DAX achieves a higher adoption level," the researchers said in their NEJM AI report.

"However, widespread implementation of DAX in its current form is unlikely to generate appreciable gains for healthcare systems looking to increase productivity."

Andrea Fox is senior editor of Healthcare IT News.
Email: afox@himss.org
Healthcare IT News is a HIMSS Media publication.