Ben Beadle-Ryby, Senior Vice President and Co-founder at AKASA, says that a typical patient record contains 50,000 words spread across 59 clinical documents. Trying to code a single patient’s conditions is comparable to reading The Great Gatsby and extracting key facts.
Historically, he says, organizations “have thrown armies of people at the problem.” Not only is that unfeasible; these people are not as accurate they need to be. Due to this and other reasons, claim denials have increased from 9.8% in 2019 to 12.7% now. Other revenue cycle measures have also gone in the wrong direction: for instance, cost to collect has gone from 2.7% in 2019 to 3.7% today.
This video at the AHIMA Annual Conference interviews Beadle-Ryby along with two clients: Nick Judd, Senior Director, Revenue Cycle and Health Information Management at Cleveland Clinic, and Jennifer Nicholson, Assistant Vice President, Revenue Cycle and Health Information Management at Duke University Health System. They talk about leveraging generative AI solutions for coding and the benefits of leveraging this technology.
Judd has experienced many previous types of automation and highlights LLMs as significantly different: “unlocking the clinical narrative” and opening up unstructured information. The LLMs adapt quickly to their setting and become more sophisticated over time.
Nicholson said that the first phase of their gen AI pilot has gone well, demonstrating improved accuracy and efficiency, and that they are beginning a second phase.
Both hospitals are applying the AI solutions to complex in-patient cases, using AI to help staff, not replace them.
To improve revenue, claims must create a “clinical narrative.” Nicholson speaks of finding “nuanced details” that improve the claim. And Beadle-Ryby wants the AI result to “show the great care” that hospitals are providing.
In the future, Beadle-Ryby hopes that AI tools can address labor shortages by improving efficiency and productivity. Both Cleveland Clinic and Duke University Health System are planning to apply AI to new areas, including denial management.
Check out our video interview below to learn how generative AI is being applied to coding.
Learn more about Cleveland Clinic: https://my.clevelandclinic.org/
Learn more about Duke University Health System: https://www.dukehealth.org/
Learn more about Akasa: https://akasa.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.
Akasa is a proud sponsor of Healthcare Scene.
