AWS and 3M Join Forces to Automate Clinical Note Creation

We recently noted the announcement of Amazon’s AWS HealthScribe with 3M as a partner that’s leveraging the solution.  The combination of these two companies was extremely interesting to me since you may recall that 3M acquired a company called M*Modal which has been working in the voice recognition space for a while.  I figured it was only a matter of time before 3M advanced its ambient clinical voice solution to compete with Nuance’s DAX solutions, Ambience Healthcare, Suki, and OnPoint Healthcare Partners to name a few.

To learn more about this announcement we sat down with two leaders at 3M and AWS to talk about the collaboration that led to AWS HealthScribe: Detlef Koll, vice president of global research and development for 3M Health Information Systems, and Tehsin Syed, general manager of Health AI at Amazon Web Services.

As expected, Koll, who was previously CTO and Founder of M*Modal, shared with us that the opportunity to do what 3M and AWS are able to accomplish today was something he saw coming a few years back, but the technology wasn’t there yet.  Now it is and so that’s why he was excited to partner with AWS to bring this solution to the market.

AWS HealthScribe does much more than make a transcript: It generates what Syed calls a “preliminary doctor’s note” using modern generative AI techniques.  In the case of 3M, they take the note that AWS HealthScribe generates and they verify the quality using a scribe.  They feel this is an important step to ensure the quality of the note.  However, Syed expects that other users of HealthScribe will offer the note straight to the doctor with no human in the loop.

Significantly, the AI generated note links each piece of information—the chief complaint, for instance—back to the place in the transcript from which it came.  This is a powerful option that allows the person reviewing the note to find the context for that AI generated piece of information. According to Syed, this builds confidence in the system as well as allowing a physician or human scribe to check the accuracy of the note more easily.  This is a unique feature that I hadn’t heard about any other solution doing.

AWS HealthScribe is also aimed, as Syed says, to address “scale, reliability, security, and data management.” Koll says they have to “ensure quality across thousands of physicians.”  Initially, they have focused this solution on general medicine and orthopedics.

Watch the video to hear the interviewees’ insights into developing patient and doctor trust, expected trends in generative AI for health, and work with EHR vendors to incorporate notes directly into the EHR.

Learn more about 3M Health Information Systems: https://www.3m.com/3M/en_US/health-information-systems-us/

Learn more about Health AI at Amazon Web Services: https://aws.amazon.com/health/solutions/health-for-data/

Listen and subscribe to the Healthcare IT Today Interviews Podcast to hear all the latest insights from experts in healthcare IT.

And for an exclusive look at our top storiessubscribe to our newsletter.

Tell us what you think. Contact us here or on Twitter at @hcitoday. And if you’re interested in advertising with us, check out our various advertising packages and request our Media Kit.

About the author

John Lynn

John Lynn is the Founder of HealthcareScene.com, a network of leading Healthcare IT resources. The flagship blog, Healthcare IT Today, contains over 13,000 articles with over half of the articles written by John. These EMR and Healthcare IT related articles have been viewed over 20 million times.

John manages Healthcare IT Central, the leading career Health IT job board. He also organizes the first of its kind conference and community focused on healthcare marketing, Healthcare and IT Marketing Conference, and a healthcare IT conference, EXPO.health, focused on practical healthcare IT innovation. John is an advisor to multiple healthcare IT companies. John is highly involved in social media, and in addition to his blogs can be found on Twitter: @techguy.

   

Categories