Ambient Voice Accuracy Lies in the Details

Terry Ciesla, Senior Vice President at ScribeEMR, explains in this video how various AI scribes can be evaluated on the basis on how well they handle complex, obscure, and subtle details.

He offers an example of a demo in which ScribeEMR’s ScribeRyte AI product accurately diagnosed a rare disease from East African, Leishmania, and then suggested a prescription and coded the diagnosis.

In another case ScribeEMR correctly recorded where to send a prescription in a complex situation.

Ciesla claims that ScribeEMR is “near or at 100% accuracy.” They are now being used in a workers’ compensation agency, where documents have to be extremely accurate in order to be used in legal challenges.

ScribeEMR is easy to learn and runs on an iPhone. The doctor can check the output themselves or through a human transcriber, who will submit results within one hour.

Customization can be provided through templates. And over time, ScribeEMR learns what details are edited out by the doctor and omits them from future notes. It can handle insurance documentation too.

They use FHIR as well as older messaging protocols to integrate their results into the EHR, and are currently working on tight integration with Epic. If they can’t load the data into the proper EHR fields through an API, they can store the doctor’s note as a PDF.

ScribeEMR is particularly popular currently in orthopedics, but they are also in dermatology, family medicine, and other disciplines.

Learn more about ScribeEMR: https://www.scribeemr.com/

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 stories, subscribe to our newsletter and YouTube.

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.