Measure your identity data management maturity. Take our 5-minute maturity assessment now

How did patient matching become a national imperative?

Policy

A few years ago, patient matching was a challenge addressed by health information management professionals within the four walls of their hospitals and health systems—typically without any oversight from the executive suite. Today, accurate patient matching has become a national imperative. Organizations like the Office of the National Coordinator for Health Information Technology (ONC) and the College of Healthcare Information Management Executives (CHIME) have sponsored patient matching competitions with prizes as high as $1,000,000. And in early October, five US senators wrote a letter to the Government Accountability Office (GAO) urging it “to consider how ONC could improve patient matching by considering the application of a national patient matching strategy.”

What happened? How did patient matching escalate from being an organization-wide challenge in the domain of health information managers to a national imperative in the domain of US senators?

The answer is that there has been a veritable perfect storm—a confluence of factors that has created an inflection point both in the ability of healthcare organizations to match patients to their records, as well as in the consequences of an inability to do so.

Let’s examine these factors.

First, federal health policy has driven the executive suites of healthcare organizations to focus on strategic initiatives that all fundamentally rely on accurate patient matching. Patient engagement, population health, interoperability, health information exchange, accountable care, precision medicine—foundational to all of these initiatives is the ability to identify and link a patient to all of his or her health records. For example, two organizations cannot exchange health records if they cannot verify that they are exchanging records for the correct person. And a hospital cannot analyze its patient population if it doesn’t know which health records belong to which member of that population.

Second, an explosion of patient data has made patient matching much more challenging for organizations. They are receiving more patient data from more sources, including patient portals, patient engagement applications, telemedicine, personal health records, and Internet of Things (IoT) medical devices—and of course none of this patient data subscribes to the same standards, shares the same formats, or has the same caliber of quality or completeness. Add to this the fact that organizations are frequently merging with each other and are increasingly expected to share more patient data with payers, providers, health information exchanges (HIEs), and state and federal health agencies, and there is just too much data to be matched.

Third, conventional patient matching technologies have reached a mathematical limit to their matching abilities. These conventional technologies (called master patient indexes, or MPIs) rely on “probabilistic” algorithms that were formalized in the 1960s and that—no matter how sophisticated—can never see through errored, incomplete, and out-of-date patient demographic data to determine whether two patient records match. Essentially, these algorithms’ matching accuracy is entirely dependent on the quality of the demographic data they are comparing—and patient demographic data is of notoriously low quality. To compensate, conventional MPIs require manual human intervention for any records they suspect to be duplicates but cannot automatically match using their algorithms. This means for an organization with 5,000,000 patients, typically 250,000 to 1,000,000 “suspected duplicates” must be manually reviewed and resolved by a human. Add to this the fact that conventional MPIs take months to implement and that their algorithms must be re-tuned with each new data source, and they suddenly become a very burdensome “solution” for a problem they are mathematically incapable of solving.

To summarize: Patient matching has become much more important for the executive suite due to new strategic initiatives. And it has become much more difficult due to new data sources and business requirements. But the very technologies we rely on to match patient records have become overwhelmed by these increasing demands and have rapidly begun to fail. And this is simultaneously happening at every healthcare organization in the country.

Where does that leave us?

With decreased quality of care. With drastic implications for patient safety and privacy. With millions of dollars of lost revenue each year to denied claims. And with increased costs to our healthcare system due to systemic inefficiencies, redundant tests and procedures, and unnecessary IT and labor expenditures.

With these consequences in mind, we at Verato set out to solve the patient matching challenge at a national scale. And we built the Verato Universal™ MPI, a HITRUST-certified SaaS solution that uses Referential Matching technology to match and link your patient or member records across your enterprise with the highest accuracy rates in the industry. Simply put, the Verato Universal MPI is the most accurate, most secure, easiest to implement, and most cost effective EMPI solution on the market—and you can deploy it in as little as six weeks.

Referential Matching is a powerful new patient matching technology that Verato has pioneered and that represents a quantum leap in patient matching technology and accuracy. Rather than directly comparing the demographic data from two patient records to see if they match, Verato instead matches that demographic data to its comprehensive and continuously-updated reference database of identities. This proprietary database contains over 300 million identities spanning the entire U.S. population, and each identity contains a complete profile of demographic data spanning a 30-year history. It is essentially a pre-built answer key for all patient demographic data.

By matching records to this database instead of to each other, Verato can make matches that conventional patient matching technologies could never make—even patient records containing demographic data that is out-of-date, incomplete, incorrect, or different.

Critically, because the Verato Universal MPI is cloud-based, and because it leverages this Referential Matching technology, it can instantly be deployed as a nationwide patient matching solution.

In fact, Verato’s Referential Matching technology MPI is already being used to match patient records by HIEs that cover over an eighth of the US population. It is such an accurate and game-changing solution that many of these HIEs—which face some of the toughest possible patient matching challenges due to the size of their patient populations and the disparity of their participants—are even using Referential Matching technology to automatically find and resolve missed matches and duplicate records that their conventional EMPI technologies cannot resolve on their own.

The Verato Universal MPI has already been built to be a nationwide patient matching solution. Because of this, any conversation regarding a nationwide patient matching strategy must seriously discuss whether the Verato Universal MPI is the answer to a problem that is suddenly of critical significance to our national healthcare system.