CASE STUDY

Consolidating Data Sources to Improve HEDIS metrics

The Challenge

Quality metrics for HEDIS reporting are pulling data mainly from administrative sources even though a wealth of information exists internally at the health system. The National Committee for Quality Assurance (NCQA) is pushing for healthcare payers to focus more on data from care management systems, Electronic Health Records (EHR), and Health Information Exchanges (HIE). The shear amount of data available is daunting and many payers are not sure how to incorporate this information into their current HEDIS engines.

The Conflict


A healthcare payer organization needed to pivot from data sources delivering stale data to sources that provide more quality information needed for HEDIS reporting.

The Solution

In conjunction with the organization’s Quality & HEDIS groups, our team examined the data in their EHR, HIE, and care management systems and determined that by leveraging modern ETL technology the information from these sources could be properly transformed and mapped into both the internal HEDIS engine as well as the vended solution. This remedy would also allow for the data to be traced end to end accompanied by detailed metadata of all transformations which was needed for auditors approval.

Goals

Transform and trace the information from the various data sources into multiple engines so internal teams can validate and analysis the data for their HEDIS initiatives.

The Result

We successfully integrated EHR, HIE, and care management data into HEDIS data sets over a 3-month period. In doing so, our team ensured that the data was consistent in both systems and accurately represented member encounters. Furthermore, the merger of these data sources was associated with up to a 30% increase in CBP measure rates.

Lastly, we were able to trace and document our ETL process in a way that was comprehensive but also easy to understand. This documentation was used to gain auditor approval for the use of this data which improved the accuracy of the healthcare payer’s HEDIS reports.

Contact Us

Retail

Predictive Analytics Improve Business Outcomes for Retailers

If data is the new business currency, then predictive analytics are the means in which organizations can take control of that currency to maximize its benefits.
Retail

Artificial Intelligence (AI) Use Cases for the Retail Industry

Overall spending on Artificial Intelligence (AI) systems is projected to reach $79.2 billion in 2022, which is more than double the amount spent in 2019.
Retail

Automation Solutions Closes the Gap on Last Mile Delivery for Retailers

According to a recent retailer’s report conducted by Blue Yonder, only 14% of the 300 executives surveyed say their fulfillment locations are fully automated.