Coming of Age: Natural Language Processing in Health Plans and Payers

How to Choose the Right Natural Language Processing Solution

These days there is a lot of talk about AI in respect to Artificial intelligence, but AI has another abbreviation, Augmented Intelligence. Artificial Intelligence implies a level of machine automated processing with no human intervention whereas Augmented Intelligence is the use of technology to enhance human performance. One AI technology that has been proven to support both interpretations is Natural Language Processing, or NLP for short. This is not a new technology, in fact, Linguamatics has been successfully completing projects using NLP since 2001.

For Payers and Health plans investigating new technologies there are many areas where NLP can support improved efficiency and business insights: HEDIS medical record review for hybrid measures, Medicare risk adjustment, clinical review/medical necessity and risk stratification to name just a few. The first four areas are about using NLP to improve efficiency of often manual processes by extracting key insights from medical records and summarizing the findings; the last example is a more automated analysis of large-scale populations to identify high risk members based on Social Determinants of Health and disease severity information.

The growth of interest in NLP and AI has led to more and more businesses claiming to have AI solutions that can help healthcare organizations to make the most of their unstructured data. The question is: how do you decide which NLP offering actually works, and which NLP solution is right for you?

Key capabilities to assess when selecting an NLP platform

We've put together this blog to help you understand the key capabilities to look for when you’re choosing an appropriate NLP solution and vendor. The list below covers the top capabilities to assess based on previous conversations and frequently asked questions:

  1. Deployment on-premise or private cloud – concerns about PHI are always high on everyone’s list where member related information is concerned. Many NLP engines require documents to be loaded into the vendor’s cloud, this often raises alarms with security and compliance teams and can be avoided by on-premise or private cloud deployments.
  2. Flexibility to support multiple use cases – health plans and payers have many applications to address with NLP. An ideal system will be able to address many applications, not just Medicare risk adjustment.
  3. Transparency and traceability – having the ability to link directly to evidence that has been used to make a decision or support a review process is key. This improves trust in the NLP system for the end users who may be sceptical of new technology
  4. Not volume based – many NLP engines are based on volumes of documents or units of text and while this is low cost to start with, health plans and payers are dealing with very large document sets that may need processing in different ways for different applications. This can lead to very high costs. Having a licensing model that allows you to process as much data as you want is important.
  5. Freedom to extend and expand functionality – health plans and payers have sophisticated analytics and IT teams who often prefer to be in control of how their data is processed and where. They also want to be able configure systems to the exact way they want to work and be able to make changes without needing the vendor to come back in or wait for a product update. Highly configurable NLP engines with advanced training are valuable because they put the client in control.

These are our thoughts, what capabilities do you look for in an NLP vendor? If there are any considerations you think are missing please, get in touch.

CONTACT US


If you’d like to find out more about the specific solutions NLP can help you with, please visit our Solutions page:

GO TO SOLUTIONS