After a week at the 2026 NCQA Health Innovation Summit, one theme stood out above the rest. Digital quality is the destination, and the industry is well on its way. What filled the sessions and hallway conversations was what it actually takes to get there.
Here are the themes we heard from health plans, providers, HIEs, regulators, and NCQA.
Digital Quality Measurement: Standards Are Ready, Data Still Needs Work
FHIR, USCDI, CQL, and ECDS have given the industry a shared foundation, and federal interoperability rules mean much of the plumbing between plans and providers already exists. One panel that included CMS argued that the same FHIR APIs built for compliance can become the primary pathway for quality data, rather than a parallel stream maintained just for reporting.
But speakers were just as clear that converting today’s measures into digital formats isn’t the finish line. The harder work now is sourcing complete clinical data, mapping it well, and changing the workflows around it so it actually gets used.
How to Fix Clinical Data Mapping Errors
Data can pass every structural check and still be wrong. In one example, a routine blood count came through with a valid, correctly formatted lab code that pointed to the wrong specimen type. The mapping error happened in the EHR, so it would have looked the same in any format. FHIR improves how data moves, but it doesn’t correct errors made at the source.
The encouraging part is that many of these problems are fixable once they’re visible. Presenters showed how code crosswalks, mapping corrections, and feedback loops back to the source turned unusable data into measure-ready data. One data aggregator reported roughly a 12% lift in HEDIS-usable codes from crosswalking alone. And in some cases, what looked like missing data was really a terminology mismatch.
NCQA’s Data Quality Framework: Proving Trust Before MY 2027
Beginning with Measurement Year 2027, NCQA is moving away from primary source verification as a universal HEDIS requirement. Where data quality validation is in place, manual record-by-record review becomes a targeted tool rather than the default.
In its place is a data quality framework built around usability, plausibility, stability, and integrity, with an emphasis on catching population-level signals like drift, gaps, and implausible patterns early and close to the source. The question for plans is shifting from whether they have the data to whether they can show it’s good.
Supplemental Clinical Data: Why Timing Matters as Much as Completeness
Claims remain the backbone of quality programs, but they arrive weeks after the moments that decide many measures. Transitions of care are a clear example. A discharge starts the clock on follow-up, medication reconciliation, and readmission measures, and those are won or lost well before the claim shows up.
The organizations sharing the strongest results had one thing in common: they supplemented claims with clinical data and used it prospectively, not just at year-end. One plan described faster measure runs, analyst time freed from manual file wrangling, and meaningful rate improvements. One provider network even described big jumps in wellness visit completion after moving from retrospective chart chase to proactive outreach.
Using AI for HEDIS: Governance Over Guesswork
AI came up across many sessions. Quality measurement runs on strict rules like timing windows, exclusions, and evidence requirements, and an answer that makes clinical sense can still fail the measure. AI used in quality programs needs those rules built in, not left to a prompt.
The broader message was governance, not fear. New technology doesn’t change clinical obligations. The strongest approaches used AI to speed up the work while keeping anything that runs against patient data deterministic, auditable, and reviewed by experts. AI is only as good as the data and rules underneath it.
Clinical Data Acquisition for Health Plans: A 12- to 18-Month Agenda
Put together, these themes point to a clear agenda for payers for the next 12 to 18 months:
- Treat clinical data acquisition as core infrastructure rather than a seasonal chart chase.
- Get ready to demonstrate data quality before MY 2027.
- Get clinical data early enough to change outcomes, not just document them.
- Build toward a single longitudinal member record that quality, risk adjustment, and care management teams can all work from.
Automating HEDIS Clinical Data Acquisition with 1up Clinical Connect
This is exactly the problem 1up Clinical Connect is designed to solve, and we’re excited that it’s now live. 1up Clinical Connect helps health plans acquire clinical data directly from provider EHRs through FHIR APIs and combine it with claims into a longitudinal member record, so that teams can leverage the data for quality reporting, care gap management, and risk adjustment, with the ultimate goal of better outcomes for members. To learn more about 1up Clinical Connect, contact us to set up a discussion.
