The Washington-based Windfall well being system continues to publish research on the impression of ambient scientific intelligence (ACI) on documentation workload and burnout. Just lately, two Windfall researchers who revealed new analysis on the subject in JAMA Community Open spoke with Healthcare Innovation about their findings.
Again in August 2025, Healthcare Innovation spoke in depth with Windfall’s Maulin Shah, M.D., chief medical info officer; Scott Smitherman, M.D., M.B.A., affiliate vp, CMIO – Windfall Medical Community; and Staci Wendt, Ph.D, director of the Windfall Well being Analysis Accelerator, in regards to the well being system’s first examine on ambient scientific intelligence.
Windfall has now expanded on earlier research by performing a complete analysis of the associations between an ambient AI system (Dragon Ambient eXperience [DAX]; Nuance) and clinician productiveness and effectivity. The analysis workforce assessed the affiliation between ambient AI use and goal documentation burden, after-hour documentation, and work quantity amongst clinicians utilizing retrospective EHR encounter metadata between July 1, 2023, and March 31, 2025. By the tip of their examine interval, roughly 8% of clinicians inside the well being system have been thought-about lively customers.
In a dialog with Healthcare Innovation, the analysis workforce mentioned their findings.
“These ambient applied sciences are instruments. They are not a alternative for care, they seem to be a device for clinicians. They cannot be anticipated to unravel all the issues of doctor administrative burden,” stated Canada Parrish, Ph.D., M.S.P.H., senior scientific analysis scientist at Windfall. “In our work, we need to quantify what that impression appears like. The anecdotes and the lived expertise of clinicians matter, however what additionally issues is, will we truly see this impression? There are a selection of instruments on the market. Is sustained funding in a single device over one other warranted? There’s goal knowledge to take a look at that, however then there’s additionally the experiential knowledge from these clinicians.”
Of their paper, the researchers discovered productiveness outcomes demonstrated statistically vital variations between the pre-active and post-active ambient AI use intervals. For example, they discovered a major decline in imply time spent on notes in the course of the first month of ambient AI use.
The Medical Effectivity Profile (CEP) is an effectivity metric that’s generated by Epic itself. The researchers discovered that the clinicians’ imply CEP scores had no rapid or sustained affiliation with ambient AI use. “I believe that it was necessary with the examine to take a look at effectivity and productiveness and administrative burden from a wide range of completely different lenses, as a result of there’s not a technique and even one normal on quantify or operationalize these constructs,” Parrish stated. “For us, it was necessary to take a broad purview on this analysis to see the place we did see proof of enchancment in these metrics, and perhaps ones the place we don’t.”
Ambient AI use additionally was not related to a right away decline in after-hours documentation time, however a statistically vital sustained decline in minutes spent documenting after hours was noticed.
“There was an preliminary lower within the time spent in notes in the course of the workday, however we did not see that rapid decline in hours post-workday,” stated Robyn Husa, Ph.D., senior scientific analysis analyst at Windfall’s Healthcare Analysis Accelerator. “We suspect that is as a result of as clinicians have been considering that the AI wrote the notes in the course of the workday, so now I’ve received to go evaluate them, and so they have been spending extra time in that evaluate interval, however because it integrates extra into their workflow over time, they spend much less and fewer time reviewing it exterior of their work hours. It’s extra of a testomony to the advantages of the gradual improve in use, and the mixing into the workflow.”
There have been no associations between ambient AI use and appointments per day, however there was a right away improve in imply RVUs following lively ambient AI use.
“We noticed a right away improve of about seven Relative Worth Models,” Husa stated. “Usually, larger RVUs equate to extra providers akin to labs, imaging, referrals, and follow-ups. Some sufferers are extra advanced of their healthcare wants, and so they require extra time for these providers. So our discovering there means that clinicians who use the ambient AI scribe can maybe see sufferers like that extra effectively, or deal with these extra advanced instances, translating to extra providers. Nonetheless, there was no change in affected person quantity per day, which means clinicians weren’t being pushed to see extra sufferers, in order that they have been simply spending much less time within the documentation, permitting for the billing of extra providers for every of those sufferers. I do need to admit that one fear in regards to the introduction of one of these expertise is that the system would possibly punish suppliers for being extra environment friendly by growing the variety of sufferers they see and we didn’t see that occur right here. It simply allowed them to be with their sufferers extra.”
The researchers famous that there are completely different workflows and concerns about deploying these instruments in specialist workplaces than in main care. “The sort of device works rather well for main care suppliers or clinicians who’ve a templated workflow that they should put into the EMR. But when they’ve a specialised sort of service that they should present and doc, then the healthcare system would wish to work extra with these instruments to pinpoint assist these particular suppliers,” added Husa.
Parrish defined that the interrupted time sequence design of the examine permits people to function their very own controls. “Until you are randomizing otherwise you’re forcing folks into utilizing the device, it may be tough to quantify the impact that is impartial of those traits which will drive somebody to make use of the device,” she defined. “We all know that early adopters do look completely different than those who got here on later, however choosing an acceptable examine design helps guard in opposition to a few of these concerns.”
Husa talked about a couple of different areas for potential analysis. Future research may evaluate the a number of ambient AI instruments in the marketplace to see which options work greatest, not solely as a complete, but in addition for various kinds of clinicians, like a main care physician versus a surgeon. They might have completely different documentation wants, she stated. “One other space could be the impression of ambient AI device use on affected person experiences and notice high quality, not simply effectivity. Lastly, the present examine checked out goal productiveness measures. Canada talked about there are all kinds of how to measure productiveness. Right here we targeted on some goal ones, however we’re planning on engaged on an examination of extra subjective outcomes — what physicians themselves report about the advantages and disadvantages of AI use.”
