Person
1 episodes · 15 quoted claims
Umesh Rustogi says early customers of Dragon Copilot for nurses reported less documentation time, less documentation delay and more complete documentation.
“Our early customers adopting Dragon Copilot for nurses actually reported outcomes that include reduction in documentation time, reduction in documentation latency, improvement in the quality and completeness of documentation,”
Microsoft built Dragon Copilot for nurses as a purpose-built product because nursing workflows differ from physician workflows.
“So we recognized very early on that the nursing workflows are unique, they are different than the physician workflows.”
Dragon Copilot for nurses converts a nurse's spoken patient interaction into structured flow sheet documentation that the nurse reviews and approves before it enters the EHR.
“AI then transforms these conversations into structured flow sheet documentation, which nurses can quickly review and approve before it enters into the EHR”
Microsoft developed its change-management practices for Dragon Copilot for nurses through early collaboration with health systems including Mercy and Advocate Health.
“through our early collaboration with many of these leading healthcare organizations like Mercy, like Advocate Health and so on.”
Rustogi says nursing workflows vary by role, such as certified nursing assistant, patient care technician or registered nurse.
“individual nurses can have variations in their workflows depending on their roles, whether they are a CNA, PCT, or a registered nurse”
Organizations that adopted Dragon Copilot well gave nurses protected education time to simulate and learn the tool.
“They provided like protected education time to enable these nurses to spend some time and then simulate and learn, right?”
Rustogi reports that nurses at Mercy said narrating their care aloud, with it pulled into the EHR as structured documentation, improved the quality of their documentation.
“like many of the nurses said that by narrating their care, by caring out loud and having that care being pulled into, uh, the EHR as a structured documentation was great for that”
Rustogi gives user-level personalization as an example: some users want recording to start when they select the patient, while others prefer to start it explicitly.
“a certain group of users basically want the recording to start immediately the moment they select the patient in the application versus somebody who would say, no, no, no, I select the patient, but then I explicitly say start recording”
Microsoft began the Dragon Copilot for nurses initiative by working with about ten leading healthcare organizations.
“we basically started working with about ten of these leading healthcare organizations.”
Because each health system has unique documentation structures, Microsoft built self-service AI assessment and customization tools for nursing informatics teams.
“this led us to build various kind of self-service AI assessment or AI customization tools that the nursing informatics team at these organizations could basically use to tweak the system as needed”
Microsoft has a clinical integrity team that reviews nurse feedback on Dragon Copilot outputs and decides whether the solution needs to be adjusted.
“we have, uh, capabilities, including a clinical integrity team, which would actually review this feedback and say if something needs to be tweaked within the solution to make this better”
Rustogi says hospital flow sheet schemas have evolved over many years and can contain ambiguity about the right choice, which affects AI accuracy.
“Because these flow sheet schemas in these organizations have evolved over years, right?”
Rustogi says the AI can only document what nurses say aloud, which is why care-out-loud practice affects how much of a flow sheet is filled in.
“Obviously, the AI can only capture things that were talked about. It cannot capture things which were not talked about, right?”
Rustogi predicts the next phase of healthcare AI will move from task automation to agentic AI that collaborates with clinicians.
“I believe in the next phase of AI in healthcare, we'll we'll basically start seeing an evolution from task automation to more agentic intelligence that collaborates with clinicians, right?”
Rustogi suggests AI agents could help nurses with post-discharge follow-up on whether patients are taking medications as recommended, to reduce readmissions.
“somebody like a nurse today ends up spending a lot of time in, uh, once a patient has been discharged, right, following up with the patient”