Patient matching has been an important issue in health IT and healthcare specifically as it relates to interoperability. More specifically, the inability to match patients to their health data, no matter where it resides, has been a huge barrier to interoperability and has also resulted in patient safety risks as well as decreased provider efficiency, a press release by the Department of Health and Human Services Office of the National Coordinator for Health IT (ONC) said.
By submitting your personal information, you agree that TechTarget and its partners may contact you regarding relevant content, products and special offers.
This is why ONC launched their Patient Matching Algorithm Challenge. This challenge, an ONC spokesperson said via email, was meant to educate those in healthcare about the performance of existing patient matching algorithms, spur the adoption of performance metrics for developers, and positively impact other aspects of patient matching including deduplication and linking to clinical data.
The winners of this challenge were recently announced and, in addition to acknowledging these winners, valuable insights were revealed about the algorithms currently being used in patient matching, the ONC spokesperson said.
The winners of the Patient Matching Algorithm Challenge included Vynca, a company that offers advanced care planning solutions, PIC-SURE, a patient-centered information commons, and Information Softworks, a company that specializes in enterprise data architecture, data warehouse design and implementation, and process automation
“Many experts across the healthcare system have long identified the ability to match patients efficiently, accurately, and to scale as a critical interoperability need for the nation’s growing health IT infrastructure. This challenge was an important step towards better understanding the current landscape,” said Don Rucker, M.D., national coordinator for health information technology at ONC, in the release.
This was an important step because the patient matching algorithms each competitor, and winners, used was different. For example, some used machine learning techniques while others a significant amount of manual adjudication.
“PICSURE used an algorithm based on the Fellegi-Sunter (1969) method for probabilistic record matching and performed a significant amount of manual review,” the release said. “Vynca used a stacked model that combined the predictions of eight different models. They reported that they manually reviewed less than .01 percent of the records. Although Information Softworks also used a Fellegi-Sunter-based enterprise master patient index (EMPI) system with some additional tuning, they also reported extremely limited manual review.”
ONC plans to hold a webinar soon that will focus on their current patient matching efforts.