Health Language Blog

Are you Dealing With Lackluster Data Analytics?

Posted on 04/18/16

Missed_Target.jpeg A recent HealthITAnalytics.com article, “Quality Metrics, Data Analytics are Top Value-Based Care Fears,” highlighted some of the problems that health systems and ACOs are having with data management and analytics. Author Jennifer Bresnick wrote, “...providers confess that the big data analytics competencies required to make the most of value-based reimbursements may be too much for them to handle.”

In fact, the article references a recent Xerox Healthcare Attitudes 2016 survey that revealed that 80% of providers “expressed some level of uncertainty about not being able to leverage their patient data for improved outcomes.” Additionally, the same number of providers said “a lack of claims data transparency may inhibit their ability to perform comprehensive data analytics and population health management.”

Maximizing Your Data Analytics in the Paradigm of Value-Based Reimbursements

Although hospital and health system executives are increasingly recognizing the opportunities of value-based care, they also understand the challenges.

Trepidation is understandable. Interoperability and data management challenges exist that must be overcome to make data useable and to produce accurate reports. The reality is that most health systems manage 40 or more clinical, claims, and administrative systems—all with their own inherent language.

Thus, one of the first steps to producing effective data analytics is overcoming terminology barriers that keep systems from communicating in a meaningful way. Provider organizations are increasingly recognizing the need for enterprise-level management of the many different terminology standards and custom, or proprietary, codes that represent the same data element across disparate systems. For instance, if a health system wants to track hemoglobin A1c values across multiple facilities and organizations, the representation of this measurement could appear a number of ways— “HbA1c” by one institution, “A1c” at a second, and “glycosylated hemoglobin” at a third. As such, this data must be “cleaned” or normalized to an industry standard to ensure accuracy with data analytics.

Terminology challenges like this one are not lost on provider organizations. The Xerox study revealed that 64 percent believe better access to clinical data will be critical to success within the value-based landscape, followed by physician-centered quality data and claims data. In fact, more than one-third of providers are “very concerned” about how they will measure quality performance and outcomes data.

For many organizations, the business case for leveraging expert consultation services and an advanced enterprise terminology management platform like Health Language® is obvious. Tools like LEAP Map Manager from Health Language exist to automate the data normalization process and provide a platform for meaningful systems communication. By automating standard clinical terminology into healthcare software applications or data warehouses through real-time auto-mapping and integration technologies, data can be safely exchanged and accurately analyzed. The end result is an effective platform for data analytics, which ultimately equips healthcare organizations with the information needed to improve care delivery and lower costs.

 data normalization

 

Topics: Analytics

About the Author

Christy Green has 15 years of career experience in the Business Intelligence and Analytics field. At Health Language, she leads a team of Consultants and Project Managers in assisting customers solve their terminology management problems. She has published other articles about analytics in Healthcare, including “Avoiding One of the Most Common Analytics Pitfalls.”