Fully Automated Medical Scribes Using AI

As most of you know, I’m a huge fan of all the efforts going on to improve the physician documentation process.  It’s a burden that’s burning out physicians.  One of the biggest efforts out there right now is called Ambient Clinical Voice.  The biggest player in this right now is Nuance (now part of Microsoft) and their DAX product (They like to call it ambient clinical intelligence).  3M through MModal is playing in this space as well.  Suki is another AI assistant that’s taking a very different approach to the problem.  Plus, there are also a number of scribe companies literally putting people in exam rooms to address the issue.  In other words, there are a lot of companies working on this problem since the documentation burden on clinicians is real.

One of the biggest challenges of ambient clinical voice is that while the technology is listening to the conversation in the exam room, the back end solutions today are using a mix of technology and people (essentially remote scribes) to create the note.  For the end user, the note is created automagically for them.  However, it’s not as automated as the user may think.

Why is this a problem?  The problem is two fold in my view.  First, if there are humans doing the work in the backend, that means that you can’t use technology to drive the cost of the service down.  Sure, the AI can make the humans more efficient and effective, but it still means that ambient clinical voice using this approach will be expensive.  The question has always been out there.  Can the backend humans be replaced by technology?  If they can, then the cost to provide ambient clinical voice will be driven down.  If they can’t, then pricing becomes an issue for many organizations.  There are lots of views on this out there, but looking at prices for ambient clinical voice today, this is still to be determined.

The second major problem of humans in the loop with ambient clinical voice is that it means there’s a delay in getting the notes completed for the doctor.  Even a 20-30 min delay is an issue.  This causes two major workflow challenges.  First, the doctor still has to go back and finalize the note they get from the ambient clinical voice well after the visit.  Not a massive issue since doctors are largely used to charting patients well after the visit, but still not ideal and could lead to mistakes.  Second, the real time clinical decision support alerts and the coming value based care alerts often depend on the data that’s being inputted into the note.  None of these happen if the note isn’t completed in real time during the visit.

With this as background, you can understand why I was intrigued by a new company called Ambience Healthcare which just came out of stealth mode with what they describe as fully automated AI medical scribes.  Rather than describe their approach and solution myself, I hopped on camera with Mike Ng, Co-Founder & CEO, and Nikhil Buduma, Co-Founder & Chief Scientist at Ambience Healthcare to learn more about how they’re approaching this EHR documentation burden problem.

In the video interview they share about Ambience Healthcare and how their solution fits between things like Human Scribes, Ambient Clinical Voice, and EHR templates.  They also share what the workflow looks like for a clinician using their product and how much of the backend technology is done by humans versus technology (Spoiler Alert: It’s all Technology done in real time).  We also talk about whether a clinician has to change the way they talk in the exam room for this solution to work and how they approach building trust with clinicians in the accuracy of the notes that are generated.

It’s still early in the life of Ambience Healthcare since they just came out of stealth mode, but I think many will be interested to check out a demo and see if it can solve some of the issues I identify above.  Check out the video interview to learn more about Ambience Healthcare’s solution.

Learn more about Ambience Healthcare: https://ambiencehealthcare.com/

Check out other articles on ambient clinical voice:

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