The challenge of big data and the solution of patient matching

Nov. 20, 2018
Erin Benson Director, Market Planning and Engagement, LexisNexis Risk Solutions – Healthcare

The average hospital faced $1.5 million in denied claims resulting from inaccurate patient identification in 2017, according to a Black Book survey. The same survey found the average cost of repeated medical care due to duplicate records was $1,950 per inpatient and over $800 per emergency room patient due to identification missteps.1 Clearly, inaccurate linking and matching of patient records is costly.

Healthcare organizations are seeking to improve interoperability to offer more coordinated care to their patients, but a foundational piece of achieving the benefits of interoperability is being able to match data across systems. Overrun with information, providers are negotiating obstacle-course-like challenges of identification and reconciliation of patient records. Practices have the ability to offer more efficient care across the continuum but data fragmentation puts both patient safety and privacy in jeopardy.

Even though interoperability remains an industry-wide challenge, providers can be proactive in their quest to achieve a fully integrated care delivery system through better, cleaner patient records. Most systems are wrought with duplicate—and thus incomplete—records and mismatches. To support patients fully, these records must be linked and matched to create one accurate portrait of each person’s health journey over a lifetime of care episodes.

Consequences of misidentification

Patient misidentification is a result of a complex data management problem, originating from incorrect or incomplete information and mismatches. Complications often arise when disparate systems’ records are merged, or when the patient is admitted (or re-admitted) to a health system. If a patient isn’t an immediate match by name or system default, the tendency is to “quick fix” the situation by creating a new patient entry. Often, another record already exists, meaning duplicate records will now spread a patient’s health data over multiple charts. When that happens, any given record pulled up during a care episode will only represent a small snapshot of health history, possibly lacking important details such as allergies, prescriptions, and previous lab or imaging results.

Similarly, transcribing oral demographic data such as patient name, birthdate or social security number is an error-prone process. Humans are known to mistype, misspeak, and, mishear. Additionally, various systems are riddled with inconsistencies on how to handle middle names or initials, suffixes such as “Jr.” or “Sr.”, or hyphens in names. How can they be sure they’ve got the right “Joseph Smith,” and that his file’s data has not been comingled with that of the 12 same-named patients in the health system?

Incomplete or mismatched data points jeopardize patient safety. Preventable medical errors are the third leading cause of death in U.S. hospitals, causing an estimated 440,000 deaths per year.2 A recent survey by ECRI Institute Patient Safety Organization of 7,600 wrong-patient events by 181 health organizations found that 9 percent of them resulted in death or harm to the patient. The organization concluded that “proper patient identification confirmation at every step of clinical care is vital to patient safety.”3

Patient linking technology

ECRI noted that patient identification errors can be avoided “through improving usability of physical, electronic, and assigned patient identifiers; use of well-designed identification alerts during order entry; and technologies and automated algorithms that function as systems-level safety checks.”

Patient-linking technologies work by analyzing records from disparate data sources and linking them together to a common patient. The technology provides a very valuable function: decreasing content volume while increasing content quality. There are various methods to linking data with varying degrees of sophistication. At its core, linking technology utilizes various analytics models and data matching techniques to link and match records. The most sophisticated techniques also rely on statistical analysis and utilize rich referential data to improve the technology’s ability to uncover similarities and relationships among patient records, while eliminating false positives and false negatives.

Working with the right data management partner to leverage sophisticated linking automation technology, combined with extensive referential data aggregation capabilities can simplify the very complex patient identity matching problem to deliver what providers need: Clean patient files, complete records and connected data via a repeatable process. Further, utilizing patient linking technology to produce a unique patient identifier that is not dependent on the patient’s Social Security number enables greater patient privacy and safety in this environment rich with cybercrime.

Practice integration

Not only does patient linking offer patients more safety and security, it offers providers multiple practice benefits. Correctly matched patient records can increase productivity in care delivery—today, clinicians waste on average 28.2 minutes per shift searching for correct medical records for patients.4

Similarly, providers risk “losing” patients in the system and have difficulty contacting them when data is incorrect. Over 35 million people move annually5, 21 million people make employment changes, and 3 million people change their marital status each year6. By having a solution in place that regularly cleanses and updates contact data, providers can maintain integrity of their patients’ demographic information and improve patient outreach and engagement, as well as achieve general process improvement that can lead to cost savings.

Accurate patient records afford care providers the critical ability to assess a person’s whole history of conditions, diseases, medical images and test results, surgeries, medications and family background to provide that patient with the best possible care. Having comprehensive, correct information automated at their fingertips can help physicians make well-informed care decisions for targeted treatment plans with confidence. They, too, can share the record with their patients, enabling engagement and optimal personal health management.


  1. PR Newswire, Improving Provider Interoperability Congruently Increasing Patient Record Error Rates, Black Book Survey.
  2. Imprivata Blog, 4 statistics that prove there’s a patient identification crisis.
  3. ECRI, Patient Identifcation Errors.
  4. Imprivata, The real cost of patient misidentification.
  5. United States Census Bereau, CPS Historical Geographical Mobility/Migration Graphs
  6. LexisNexis Risk Solutions – Health Care Patient Data MasterFile.

Sponsored Recommendations

A Cyber Shield for Healthcare: Exploring HHS's $1.3 Billion Security Initiative

Unlock the Future of Healthcare Cybersecurity with Erik Decker, Co-Chair of the HHS 405(d) workgroup! Don't miss this opportunity to gain invaluable knowledge from a seasoned ...

Enhancing Remote Radiology: How Zero Trust Access Revolutionizes Healthcare Connectivity

This content details how a cloud-enabled zero trust architecture ensures high performance, compliance, and scalability, overcoming the limitations of traditional VPN solutions...

Spotlight on Artificial Intelligence

Unlock the potential of AI in our latest series. Discover how AI is revolutionizing clinical decision support, improving workflow efficiency, and transforming medical documentation...

Beyond the VPN: Zero Trust Access for a Healthcare Hybrid Work Environment

This whitepaper explores how a cloud-enabled zero trust architecture ensures secure, least privileged access to applications, meeting regulatory requirements and enhancing user...