As CMS moves towards 100% encounter data in risk adjustment calculations next year, the ability to extract relevant information from clinical records will become paramount. While payers dread this upcoming change in Medicare Advantage and Part D calculations, all is not lost. In this article, we will identify a few key innovations these organizations can implement to stay ahead of all the changes coming down the pipeline.

The Pitfalls of Manual Risk Adjustment

When calculating risk based on clinical notes, the current situation leaves much to be desired. To reap the most out of CMS reimbursements, care providers are working coders to the bone through manual processes that take hours and leave inaccurate results. It, in turn, leads to millions of dollars’ worth of reimbursements falling through the cracks as certain conditions are not coded for, thus frustrating both payer and provider stakeholders. Unfortunately, this has been a pattern that has been slowly increasing since 2016, when CMS began introducing encounter data slowly into risk adjustment. 2022 will present a significant challenge for all stakeholders involved as this often inaccurate encounter data will make up 100% of what is included in risk adjustment calculations.

A Respite for the Weary

Fortunately, the days of struggling through missed coding opportunities and dealing with large amounts of illegible physician notes are ending. Provider organizations can now leverage new AI technology like Natural Language Processing (NLP) and Machine Learning (ML) to get ahead of risk adjustment challenges and reap the rewards of maximized reimbursement

AI Changes the Game

Instead of fear around how AI will impact the organization’s efforts, individuals should begin to embrace it as a service that will only make the process of risk adjustment incredibly accurate and efficient at the same time. Machine learning (ML) and natural language processing (NLP) present a considerable opportunity to clear the deck and look at risk adjustment from an entirely new perspective.

Automation and Scalability

Automated coding support across the entire care continuum can lead to streamlined workflows across the whole organization. This level of scalability is inherent in ML and NLP solutions once they have been implemented into the EMR. Both clinical and financial teams become more efficient, HCC scores are improved across the entire organization, and care gaps shrink due to implementation.

Pattern Recognition

The opportunities present in natural language processing for completely changing the dynamics of how HCC coding and risk adjustment are made points to why it is such a valuable tool for payers and providers. While we are still in the early innings, how will it utilize it at scale? Early indications point towards its ability to take unstructured data from clinical notes and put it into a structured form for later inclusion into various uses, risk adjustment at a large scale being chief amongst them.

A Practical Solution

A practical solution for risk adjustment woes is to turn to a tool that includes a decade of experience with access to 30,000 evidence-based rules that can be deployed as a secure cloud-based solution. Persivia’s NLP and ML capabilities through the CareSpace® platform allow providers to take a more confident approach to getting risk adjustment scores right and submit them to CMS for maximum reimbursements. CareSpace® can run the data from hospitals through NLP and ML, extract possible diagnoses and missed codes, and combine structured and unstructured data within a longitudinal patient record.

The CareSpace® platform represents the paradigm shift in how healthcare organizations of the future will manage risk adjustment through an augmented AI-driven solution. As one of the early adopters of AI tools, Persivia has the experience and the know-how to guide payers and providers into this new era of AI-driven risk adjustment.

Are you ready to evolve with some of the top organizations in the industry? Contact us to schedule a demo today!