Linguamatics natural language processing (NLP) for Risk Adjustment combines leading healthcare NLP, a state-of-the-art curation and review interface and efficient scalability to enable organizations to transform how they accurately identify risk adjustable comorbid diagnoses.
Payers and providers can connect technology with subject matter expertise in an intuitive and easy to use workflow to increase efficiencies and ensure better confidence in their risk adjustment submissions, whether Medicare Advantage hierarchical condition category (HCC) coding or affordable care act (ACA).
The challenge of finding diseases and evidence from clinical notes for risk adjustment
Medicare Advantage, relies on accurate risk adjustments to predict the future health care expenditures of individuals based on diagnosis and demographics. The process is time-consuming and costs millions of dollars annually. At the heart of these risk adjustments are hierarchical condition categories, or HCC codes, which allow payers to identify the difference between members with different comorbid conditions (for example, diabetes without complication is much less expensive to treat than diabetic kidney disease). There are about 80 of these codes, covering approximately 10,000 ICD10 codes and the process to ensure the most granular or specific codes have been captured makes up much of the risk adjustment effort at payer organizations.
Healthcare NLP for Risk Adjustment
Linguamatics natural language processing (NLP) platform has a proven track record of uncovering diagnoses from complex medical records. Used by leading payers and providers, it supports population health and risk stratification with publication grade accuracy. Whether it is in Risk Adjustment or Precision Medicine, our NLP has been proven to uncover diagnoses with > 90% precision and recall, and to significantly reduce medical chart review time.
Risk adjustment case study - Existing Payer Customer
Curate and review to generate highly accurate results
Our Human Assisted Review Tool – HART – puts the facts in the hands of the experts. Having combed through medical records at a rate of 8 million documents per hour, conditions, codes, and risk categories are presented to the user to accept or reject. With the medical record presented in an easy to consume screen, coders can also highlight additional text and add new codes that the NLP may have missed – or alter NLP presented codes to ones of their choice. This is where expert and technology combine in true augmented intelligence.
With each code linked to associated text in the medical record, highlighted and presented to the user, an audit trail exists to back up each code submitted. If coders disagree with suggested codes, a note taking function lets them capture their reasoning should this be challenged in the future.
Not every organization has the same requirements when it comes to deployment – therefore, our solution is available in a variety of deployment models. Using the NLP Data Factory, volume is not an issue, and our NLP Risk Adjustment workflows can be configured specifically to our customer’s needs. Because we know Healthcare data is complex and often messy, there are a suite of pre-processors to deal with the different sources and formats that payers receive data in. Whether that is Optical Character Recognition (OCR) correction for scanned PDFs, or region detection for Consolidated Clinical Document Architecture (CCDAs), we have the tools to ensure that the highest accuracy results are obtained.
Beyond CMS Risk Adjustment
Many organizations are thinking about NLP not only for Centers for Medicare & Medicaid Services (CMS) Risk Adjustment, but for far broader reaching applications. From extracting member level SDOH data to providing additional features for predictive models; from sentiment analysis in call center transcripts to mining broader datasets such as FDA drug labels to gather information on reported adverse events – NLP is becoming a core competency. Our NLP platform offers flexibility across multiple use cases, allowing organizations to adopt an enterprise strategy for unstructured data.