Company profile
CyncHealth is a health data utility (HDU) and designated health information exchange (HIE) connecting over five million lives and 1,100 facilities across Nebraska and Western Iowa. It is committed to providing a fast, reliable network for accessing critical patient data to enhance patient care and efficiency across a diverse range of healthcare organizations while also fostering healthier communities.
The challenge
CyncHealth’s mission is to enable healthcare data exchange to help clinicians deliver comprehensive, effective patient care. However, like many in the industry, they have struggled to extract greater value from the highly variable information they aggregate from multiple sources.
As patient data is gathered and moved across health information systems, it often loses key components such as standard codes. CyncHealth found that cleaning and reformatting this inconsistent patient data was a cumbersome, manual process that sometimes delayed decision-making in patient care. Furthermore, the loss of specific codes and other metadata was leading to suboptimal patient outcomes and experiences, causing frustration among patients within their network. To solve this problem – and expand and improve the services they offer their clients – CyncHealth needed higher quality data.
The solution
To improve the experience for those in their network, CyncHealth leveraged IMO Health’s normalization engine to address its data quality challenges. Built on industry-leading terminology that incorporates more than five million terms and comprehensive mappings to all major code systems, IMO Precision Normalize standardizes and enriches inconsistent clinical data at scale to unlock additional value. Through this partnership, IMO’s solution alleviated the burden of cleaning patient data within CyncHealth’s analytics-enabled data warehouse (EDW).
Since implementing IMO Precision Normalize in 2020, nearly half (48.6%) of all normalized patient diagnoses within the organization’s EDW have become more specific than the ICD-10-CM codes already present in their data warehouse. IMO Precision Normalize has also been incorporated into CyncHealth’s real-time data collection process. As a result, 83.7% of that data is now automatically coded, at a sufficiently high confidence level, without any human intervention. By accessing more comprehensive and accurate data, analysts have been able to focus on quickly extracting valuable insights to enable more effective responses to population trends. Providers within CyncHealth’s system can now also access a wider range of patient information, empowering them to make better decisions for their patients and communities.
“I’ve long held that embedded terminology services are a critical component of the value that we can provide our participants and data recipients,” says Naresh Sundar Rajan, Ph.D., Chief Data Officer at CyncHealth. “Ensuring we standardize and enhance data to make better decisions is crucial to our mission of advancing interoperability and bringing data democratization. We’re excited to extend our valued partnership with IMO Health, as they bring a unique approach to terminology, high adoption within our participant base, and flexible deployment models, thus improving the health of our communities.”
Since implementing IMO Precision Normalize in 2020, nearly half (48.6%) of all normalized patient diagnoses within the organization’s EDW have become more specific than the ICD-10-CM codes already present in their data warehouse.
Looking forward
Given the success CyncHealth has had with IMO Precision Normalize, the organization is looking to expand its use in the following ways:-
Create a plan to add real-time API capabilities to interface engines in their network for rapid standardization of clinical data
-
Integrate IMO Precision Normalize into a central EHR system interface engine to improve data quality to better understand traffic patterns and identify ROI opportunities for clients
-
Audit the standard codes used in EHR systems to catch data quality issues early and identify data performance benchmarks
