ONC initiating Patient Matching Algorithm Challenge Next Month

Identifying that the misidentification of sufferers remains a difficult issue for healthcare agencies, the Office of the National Coordinator for Health Information Technology is planning to start its Patient Matching Algorithm Challenge early next month.

“There is a lot of work going on with patient matching in the industry,” claims Steve Posnack, director of the ONC Office of Standards and Technology. “But with all the matching that is gone on, there are some benchmarks that are publicly available … about how well the algorithms that individuals are using to do sufferer matching should perform.”

Posnack explains patient matching as the procedure of comparing different demographic elements from different health information technology systems to evaluate if they refer to the same patient. He also appreciates the potentially negative effect that mismatching can have on patient safety.

The target of ONC’s Patient Matching Algorithm Challenge is to shine “a little bit of sunlight and transparency around what the benchmarks should be and how well the present tools are performing (and to) see if there are other tools and algorithms out there that could do a great job potentially than what is presently in use,” Posnack asserts.

The fial goal of the challenge is to “spur the establishment of innovative new algorithms, benchmark current performance and assist the industry coalesce around common metrics for success,” in accordance to Posnack.

Participants in the challenge, which officially initiates in early June, will be offered a dataset and will have their answers evaluated and scored against a master key. These participants will be offered as many as 100 run-throughs to see how well they can match the sufferers in the dataset.

ONC will award as many as 6 cash prizes totaling $75,000. The huge prize category will engage 3 prizes for the highest “F-Score”—a combination of best precision and recall. Additionally, best in category prizes will be awarded for “best precision” (least mismatched patients), “best recall” (least missed matches) and “best first F-Score run.”

Previously this year, the ECRI Institute ranked the top 10 patient safety concerns in the year of 2017 for healthcare agencies, with patient identification errors ranking 6th overall.

Posnack points out that the College of Health Information Management Executives has initiated and is currently conducting a $1 million National Patient ID Challenge designed to establish a solution that ensures 100% accuracy of every patient’s health data to decrease the preventable medical errors.

He explains ONC’s Patient Matching Algorithm Challenge as being complementary to the CHIME’s National Patient ID Challenge, with finalists in the innovation round to be declared on May 12 and an ultimate winner declared in the month of November.

“We’ve a great relationship with CHIME and have surely been in touch with them related to their challenge,” adds Posnack. “But, we are approaching patient matching from a different angle. We are actually trying to spotlight how the algorithms perform and the benchmarks that we can develop from an industry perspective.”

ONC will conduct 3 informational webinars—May 10, 17 and 24—to give additional details about the challenge and participant requirements.

“We expect our challenge will get the attention of experts from other industries that deal with individual matching, like the financial and airline industries,” Posnack summarizes.