Hierarchical Condition Category (HCC) coding plays a pivotal role in federally regulated risk adjustment payment models, ensuring accurate reimbursement for health insurance plans and better care for managed populations. Providers are essential in this process, as effective collaboration with health plans leads to improved patient outcomes. Traditionally, electronic medical records (EMRs) served primarily as data repositories, but technological advancements, particularly in Natural Language Processing (NLP), have transformed their utility.

This presentation will explore how WVU Medicine has harnessed unstructured patient data within their EMR system to accurately assess and assign HCC codes. By leveraging NLP models from John Snow Labs, WVU Medicine was able to identify and extract relevant HCC codes from clinical notes, subsequently providing these codes to physicians through best practice alerts. This innovative approach has significantly streamlined HCC coding, reducing the burden on providers while enhancing the accuracy and efficiency of the process.