Demonstrating the value of terminology-based normalization for cohorting patients

Clinical terminology plays an important role in EHRs and provider workflows. But what about when it comes to cohorting patients?
Clinical terminology plays an important role in EHRs and provider workflows. But what about when it comes to cohorting patients?

As an industry leader in clinical terminology, IMO has engaged with the informatics research community for nearly 30 years. At this year’s American Medical Informatics Association (AMIA) Annual Symposium, we presented a study showing how our terminology-driven normalization engine improves diagnosis coding for electronic quality reporting and cohorting patients.

Improving the reporting process to lead to better reimbursements

Many providers today struggle to submit the electronic clinical quality measures (eCQMs) that are required by many CMS programs. The goal of our study was to determine whether we could improve a provider’s reporting process with a terminology-driven normalization engine. Because the inclusion or exclusion of the wrong patients could significantly impact the final eCQM performance measure, properly identifying these patients is critical to getting the right reimbursement and avoiding penalties.

The role of patient cohorting

The question then becomes, how can we help providers be sure that they have found the right patients to use when calculating their eCQMs after searching through their EHRs. Diagnoses are often documented in multiple locations in the EHR with varying levels of specificity. What’s more, it’s not uncommon for some important details – like severity, staging, or chronicity – to be missing pieces of information. But these details can make all the difference when it comes to eCQM reporting.

Clinicians often annotate these diagnoses in free text in order to provide more nuance. But these annotations are typically captured in a separate field and written in unstandardized language – meaning extracting and coding the information documented in free text can be extremely time-consuming and error-prone.

Putting normalization to the test

IMO set out to find a solution. We hypothesized that by using a normalization engine to extract terms directly from the annotated diagnosis field, we would be able to preserve clinical intent when documenting the patient’s diagnosis. This in turn would lead to more accurate diagnosis codes overall, helping providers properly include or exclude patients when specifying a cohort.

Normalization preserves clinical intent, essential details

Overall, we found that using IMO Precision Normalize allowed us to preserve the clinician’s intent, represent complex conditions more accurately with multiple codes, and capture key details necessary for accurate patient exclusion. This illustrates the value terminology-based normalization has for providers looking for effective, demonstrated solutions to ease the reporting process while ensuring appropriate reimbursement.

Read more about the value of normalization terminology in our post, Enhancing data quality initiatives throughout the healthcare ecosystem.

Ideas are meant for sharing.

Sign up today and have Ideas delivered straight to your inbox.

Latest Ideas​

Explore our blog for answers to frequently asked questions about CPT® codes, including their use, maintenance, and categories.
Struggling with data standardization in health tech? Discover how IMO Precision Normalize can seamlessly integrate with your tech stack.
A recent HIMSS Market Insights survey underscores significant gaps leaders face in managing data quality in healthcare.

IMO is now IMO Health

New name. New logo. Same unwavering commitment to data quality in healthcare.