Healthcare is poised to become the world’s fastest-growing source of data in the next year (RBC Capital Markets), accumulating from sources that are as varied as they are numerous, including hospitals, doctors’ offices, retail clinics, and wearable devices. While this wealth of information holds immense potential to revolutionize healthcare, accurately managing it is cumbersome and leveraging it effectively is challenging.
A substantial driver of this challenge is that correctly attributing the data to an individual and tying the data together is non-trivial. This, of course, is key to being able to interpret and effectively utilize all the data. Ensuring the integrity of identity information is critical – a person’s data must be accessible, accurate, consistent, and in the right context for the person receiving and using it.
Challenges in maintaining data accuracy
According to the World Health Organization, “Failure to correctly identify patients can be a root cause of many problems and has serious effects on health care provision.” The risk of duplicate, inaccurate, incomplete, or inconsistent identity data across records creates far-reaching problems. Inaccurate data causes multiple appointments or tests, as well as delays in treatment.
Unfortunately, studies indicate that errors in matching records to the correct person occur up to 50% of the time. Health tech companies need to ensure the accuracy and relevance of each piece of information they collect, regardless of the vast array of diverse institutions from which it comes.
This includes data from primary care facilities, hospitals, clinics, pharmacies, consumer-generated data, plus IT systems such as EHRs, patient registries, radiology information systems, medical devices, and more. As more data is quickly generated, the risk of inaccurate identity data also increases. Consequently, internal teams and even customers are forced to spend time resolving duplicates, which increases total cost of ownership and reduces trust in data quality.
To place this concern in context, consider an at-home glucose monitoring device. To make the data from the device actionable, information must be obtained not only from the device, but also directly from the consumer, the provider managing diabetes care, a pharmacy, and an insurance provider. It’s highly probable that each of these sources uses a different system with inconsistent data cleanliness.
Complicating this further is that a person also may be known by different variations of their name in different systems – for example, Micheal, Mike, Mickey. The complexity in matching all data from different sources and formats into a single, clean record makes the potential for error extremely high.
Effectively managing person data is table stakes
Enterprise Master Person Index (EMPI) technology plays a crucial role in addressing data matching challenges by offering a centralized repository for identity information, ensuring accurate person matching across diverse systems, data integrity, and interoperability.
For health tech companies building innovative technologies and data-driven applications, an EMPI serves as a foundational element in achieving and streamlining data accuracy within their solutions. This builds trust with customers around the quality of information delivered by (or powering) the product, especially when ingesting, integrating, and reconciling data across several sources.
Some of the more advanced EMPI solutions are beginning to leverage AI and machine learning (ML) to automatically link person records, resolving data linking and data quality issues. This reduces manual intervention by mirroring human decision-making to resolve data linking and data quality issues within an EMPI. Preferred actions are automated, improving data accuracy, consistency, and downstream credibility and reducing the workload on both data stewards and data consumers.
Deciding whether to buy or build an EMPI
To achieve growth targets and maintain customer satisfaction, successful health tech companies should be clear on and invest in their core competencies and competitive differentiators instead of sinking extra resources and developing infrastructure. Leaning on a reliable EMPI partner with a proven track record can help solve challenges around streamlining and managing increasing amounts of data – resulting in high-quality data, faster time to market, and reliable scalability.
EMPI solutions, augmented by AI technologies, offer a solid foundation for achieving accurate and consistent identification from sources across the healthcare ecosystem. For health tech leaders and development teams, EMPI technology not only adds data integrity for their customers, it also delivers efficiency and reduces risks for the product team and health tech company. Highly accurate and current personal data ensures the data decisions and analytics the product presents are backed by confident, trustworthy data.
About Jitin Asnaani
Jitin Asnaani is the Chief Product Officer at Rhapsody where he Jitin leads Rhapsody’s product strategy and execution, with a focus on accelerating digital health transformation and adoption. He has an extensive background in interoperability and digital health, leading significant industry initiatives such as CommonWell Health Alliance, the Argonaut Project, and the Direct Project. Jitin also led corporate development at Bamboo Health and Health Gorilla.
