Ohio State launching AI app to record patient and physician conversations
The health system decided to move forward with the ambient documentation after a poll found approval for the tech.
Photo: Laurence Dutton/Getty Images
After conducting a poll showing most Americans approve of artificial intelligence in healthcare, Ohio State Wexner Medical Center is launching an AI-driven application that helps clinicians draft clinical notes.
It's piloting the Microsoft Dragon Ambient eXperience (DAX) Copilot application, which uses conversational, ambient and generative AI to securely listen to a provider-patient visit and draft clinical notes in the patient's electronic medical record. Rather than the provider typing the notes during the visit, they can focus on the patient, then review and edit the notes afterward, the hospital said.
From mid-January to mid-March this year, 24 physicians and advanced practice providers in primary care, cardiology and obstetrics and gynecology tested the technology during outpatient clinic visits. After obtaining the patient's permission, the provider records the visit through the AI application. Once the visit is complete, the notes are organized and ready for review in less than a minute.
"We found it saved up to four minutes per visit," said Dr. Ravi Tripathi, chief health information officer at Ohio State Wexner Medical Center. "That's time the physician can use to connect with the patient, do education and make sure they understand the plan going forward. A few clinicians preferred their old workflow, but overall, 80% completed the pilot. In fact, we allowed them to keep using the AI solution afterward because it had significantly impacted their practices in the eight weeks of testing."
Participants in the pilot said there were some missteps, such as incorrect pronouns or mistaking one word for another, but these issues were easily fixed during chart review. They reported higher-quality time with patients and better patient interactions and care plans.
As of July 1, Ohio State expanded ambient documentation access to all providers in outpatient settings. In the first two weeks of expanded use, 100 clinicians regained 64 hours of time and satisfaction scores have improved from patients who say their conversations with their physicians were more valuable.
WHAT'S THE IMPACT?
The AI application is being rolled out alongside survey data showing that most Americans are fine with the use of AI in healthcare – with a few reservations.
Ohio State Wexner Medical Center's national poll showed 75% believe using AI to minimize human errors is important. Seventy-one percent would like AI to reduce wait times, while 70% are comfortable with AI taking notes during an appointment. Sixty-six percent believe AI should improve work-life balance for healthcare providers.
While most Americans also see value in AI for healthcare, the survey found that just over half (56%) still find it a little scary and 70% have concerns about data privacy.
THE LARGER TREND
In March, the Congressional Budget Office determined that the evidence on the usefulness of AI is mixed, particularly when it comes to costs, and that the practical application of these technologies is still inconsistent at this nascent phase – showing usefulness in predicting cancer mortality, but falling short when predicting heart failure outcomes.
CBO said its baseline projections of Medicare spending and spending on commercial health insurance reflect the trend of more services being provided in hospital outpatient departments (HOPDs), rather than physicians' offices. That long-standing trend has occurred partly because the vertical integration of hospitals and physicians has increased, and partly because more independent physicians have chosen to provide more care in HOPDs.
Meanwhile, Moody's Investors Service said last year that while AI has the potential to improve revenue cycle operations, optimizing labor through administrative efficiency and lower operating costs, it comes with the risk of cybersecurity attacks and patient data breaches
AI also has the potential to change the industry's competitive landscape, Moody's said. But unlike generative AI, most AI models are not plug-and-play, and their integration into business models are expected to take several years.
Jeff Lagasse is editor of Healthcare Finance News.
Email: jlagasse@himss.org
Healthcare Finance News is a HIMSS Media publication.
The HIMSS AI in Healthcare Forum is scheduled to take place September 5-6 in Boston. Learn more and register.