Generative AI Crucial for Coding Complex Conditions

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.

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/

Healthcare IT Community: https://www.healthcareittoday.com/