ONC launches $75,000 patient matching algorithm challenge
The Office of the National Coordinator for Health IT announced a developer contest to create patient matching algorithms.
ONC’s Office of Standards and Technology director Steven Posnack wrote on the Health IT Buzz blog that the Patient Matching Algorithm Challenge is designed to yield innovative algorithms, common metrics and performance benchmarks to address one of the biggest interoperability problems in healthcare today.
“The ability to complete patient matching efficiently, accurately, and at scale has long been identified as a key element of the nation’s health IT infrastructure. Patient matching is almost universally needed to enable the interoperability of health data for all kinds of purposes,” Posnack noted. “Patient matching also requires careful consideration with respect to its effect on patient safety and administrative costs.”
[Also: ONC posts new interoperability framework as providers vary on approach]
But Intermountain CIO Marc Probst told Politico that ONC could and should pursue other areas to benefit healthcare, notably “real solutions around standards,” rather than patient matching right now.
"This does not seem like a value add,” Probst told Politico, “but rather a reaction to garner attention and 'prove' ONC is doing something."
Developer contests typically grab attention and ONC has conducted several in the past, including for Blue Button, Blockchain and APIs that enable patients to share their data.The Patient Matching Algorithm Challenge promises a total for $75,000 for up to six winners and Posnack wrote that ONC will host informational webinars before the contest opens in June.
[Also: ONC releases 2017 Interoperability Standards Advisory]
“While numerous recommendations have been issued over the years to tackle different aspects of patient matching, it is important to recognize that the entire health care system can impact its performance – from data capture at patient registration to the technology and algorithms along the way,” Posnack added. “At the same time, there has been little transparency about how well current patient matching algorithms perform and no industry-accepted minimum baselines, benchmarks or testing approaches exist.”
Twitter: SullyHIT
Email the writer: tom.sullivan@himssmedia.com
