The Medicare Advantage (MA) landscape is entering a new chapter. For the first 25 years of the program, success was largely measured by how effectively organizations captured and supported HCCs while maintaining coding accuracy. That objective hasn’t changed. What has changed is the scorecard. As CMS expands RADV across all Medicare Advantage contracts, implements CMS-HCC V28, and increases regulatory oversight, success depends not only on how completely organizations capture risk, but also on how confidently they can defend every submitted diagnosis.
As a result, risk adjustment leaders are rethinking how they evaluate vendor performance, measure quality, and leverage technology to ensure every submitted diagnosis is appropriately documented, accurately coded, and audit-ready.
For years, vendor performance focused on three core questions:
● Did the vendor identify supported incremental HCCs?
● Were those coding recommendations accurate?
● Were unsupported diagnoses appropriately identified and recommended for deletion?
These measures remain important, but they no longer tell the whole story.
Leading Medicare Advantage organizations have always balanced identifying incremental HCC opportunities with removing unsupported diagnoses. But as audit scrutiny has increased, many plans now place greater emphasis on proactively identifying unsupported diagnoses before final submission.
As a result, health plans are rethinking and expanding how they evaluate vendor performance. The conversation is no longer limited to, “How many HCCs did this vendor find?” Leading organizations are also asking, “How much value did they leave behind?” and “How much unsupported RAF did they help us avoid?” Those questions are redefining the scorecard by which coding vendors are evaluated, but they are difficult to answer using traditional quality assurance processes.
Most QA programs still rely on manually reviewing a sample of charts after coding is complete. While sampling can identify trends, it provides limited visibility into overall coding performance and often delays feedback until after projects have been completed.
Quality assurance is now evolving from a retrospective audit function into a continuous performance management capability, and AI is making that shift possible.
Rather than asking reviewers to manually search thousands of charts, AI can rapidly organize medical records by encounter, surface evidence supporting HCCs, identify potential missed diagnoses, and flag unsupported conditions for targeted review. This enables experienced coders to focus on validating documentation and coding decisions rather than manually searching thousands of pages for relevant encounters, while also allowing organizations to evaluate a much larger percentage of their coding population than traditional QA methods permit.
The result is faster feedback, greater consistency, and increased confidence that submitted diagnoses are both complete and defensible.
As regulatory expectations continue to evolve, the organizations that will be best positioned for success are those that continuously measure coding quality, identify variation early, and provide actionable feedback that improves both coding accuracy and audit readiness.
Accurate coding has always been the objective. The difference today is that organizations must be able to prove it—at scale.
To learn how AI can evaluate your vendor performance within days of project completion, schedule a consultation with one of Charta’s risk adjustment AI deployment specialists.
At the Becker's 5th Annual Fall Payer Issues Roundtable, taking place November 2–3 in Chicago, payer executives and healthcare leaders will come together to discuss value-based care, regulatory changes, cost management strategies and innovations shaping the future of payer-provider collaboration. Apply for complimentary registration now.
