The U.S. Department of Health and Human Services’ Office of the National Coordinator for Health Information Technology (ONC) today announced advance care planning solution company, Vynca as the first place ($25k) winner of the Patient Matching Algorithm Challenge. ONC selected the winning submissions from over 140 competing teams and almost 7,000 submissions using an ONC-provided dataset.
Patient Matching Algorithm Challenge Overview
“Patient matching” in health IT describes the techniques used to identify and match the data about patients held by one healthcare provider with the data about the same patients held either within the same system or by another system (or many other systems). The inability to successfully match patients to any and all of their data records can impeded interoperability resulting in patient safety risks and decreased provider efficiency.
For the challenge, 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. The winner was based on the best “F” score, which is an accuracy that factors in both precision and recall.
Other runner-up winners included:
– Second Place ($20k): Picsure
PICSURE used an algorithm based on the Fellegi-Sunter (1969) method for probabilistic record matching and performed a significant amount of manual review.
– Third Place ($15k): Information Softworks
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.
– Best First Run ($5k): Information Softworks
– Best Recall ($5k): Picsure
– Best Precision ($5k): Picsure
The dataset and scoring platform used in the challenge will remain available for students, researchers, or anyone else interested in additional analysis and algorithm development, and can be accessed via the Patient Matching Algorithm Challenge website.
