Why referential matching could prove beneficial to health systems.
The goals proposed in the 21st Century Cures Act Trusted Exchange Framework and Common Agreement (TEFCA) proposal are positive and worthy of adoption. Patients and providers should certainly have easy access to health information. Health enterprises performing population health should absolutely have the required information they need as well. But in terms of the setting up a strong foundation to get there, TEFCA is really just kicking the can down the road.
Underlying all of the aims of TEFCA and any type of data portability is the fundamental need for universal, consistent, and reliable patient matching. We must be able to consistently and accurately answer this question: Are we talking about the same person?
The reason the industry has been unable to consistently and accurately answer that question is that current patient matching technology is just not good enough.
Most patient matching approaches rely on head-to-head demographic data comparison to make matches. This approach has been around for more than 30 years, and we’ve squeezed every last match we can from it. With a lot of manual effort and constant tuning, it serves the matching needs within the four walls of a health system because hospitals can impose very strict data standards, data governance, and tuning settings; and they can hire half a dozen “data stewards” to resolve patient matches that the algorithm cannot. Even so, hospitals still see 8 to 12 percent patient duplication rates enter their electronic health records (EHRs).
The weakness in that approach tends to get much worse when applied to networks like health information exchanges (HIEs) for two reasons. First, HIEs do not have control of their incoming data quality. They cannot impose the same degree of data format standards, data capture standards, data governance rules, algorithm tuning rules, and manual adjudication that hospitals can. So, they cannot be expected to achieve the same match rates as their contributing members.
Secondly, it is a fundamental law of data science that data quality degrades rapidly as more disparate sources contribute to a database. So, if just one hospital in an HIE network introduces an unmatchable patient identity into the HIE, then every member hospital within the HIE will now be at risk of mismatching that patient on all future queries. HIEs can manage this compounding error effect reasonably well when the number of sources is limited to a modest-sized region.
TEFCA proposes a layer above HIEs called qualified health information networks (QHINs). These QHINs would aggregate the identities contributed from hundreds or thousands of participants. Any error introduced for any given patient will be completely unacceptable for TEFCA, as all other goals—record location and retrieval, complete information sharing—will fail with the introduction of duplicate records.
An entirely new patient matching approach, called referential matching, can solve the problem of patient matching accuracy at a national scale. It does so by using a reference database of identities as an authoritative answer key against which all patient identities are compared. The reference database contains demographic information for the US population and includes a wide range of identity information for each person—nicknames, maiden names, current and former addresses, current and former phone numbers, and emails. By comparing every patient identity to its corresponding reference identity, referential matching avoids the chain reaction of errors that occur when patient records must all be matched to each other.
There is another remarkable characteristic of referential matching that will serve QHINs well, and that is its ability to inherently resolve identities between QHINs. If all QHINs use the same referential matching database (or cooperating databases), they will have mapped all their patient identities to the same corresponding reference identities. In doing so, the identities from one QHIN will be instantly cross-mapped to the identities of all other QHINs with no extra matching required. This eliminates the problem of wide disparity in matching capabilities of different EHRs and between the largest hospitals and the smallest community hospitals.
While there might be other ways to address the level of patient matching needed to meet TEFCA’s goals, we will be very hard pressed to find one that does not depend on extraordinary new technology or standards to be imposed at every hospital system—including uniform data quality standards, consistent matching rules and algorithms, and consistent use of biometric capture everywhere. Moreover, we are unlikely to find a solution that supports the smallest and largest care facilities equally well. The Referential Matching approach has the extraordinary ability to improve patient matching for every facility as well as for every QHIN.
The laudable goals of TEFCA should not be dashed simply because of inadequate and outdated patient matching technology. We need something new and better. To not act is simply kicking the can down the road.
Mark LaRow is CEO of Verato.
Get the best insights in healthcare analytics directly to your inbox.