Leveraging Open-Source Matching Tools and Health Information Exchange to Improve Newborn Screening Follow-up

Public health and clinical stakeholders are increasingly recognizing the value of sharing data among health information exchanges (HIE) and public health. Robust patient matching is a core HIE function required for aggregating patient data across disparate systems and such functionality can also be leveraged for a variety of processes of value to public health. While one well-known public health process is matching immunization data, an additional use case involves improving newborn screening follow-up by identifying infants who may lack screening. It is well-known that not all infants are appropriately screened for harmful or potentially fatal disorders that are otherwise unapparent at birth. Although public health authorities can link vital records data with newborn screening results to identify unscreened infants, such processes may be delayed and some cases may remain undetected by this process. To improve detection of unscreened infants, we have implemented a pilot process to verify that all infants within the Indiana Network for Patient Care (an operational regional HIE) have a newborn screen present. To accomplish this, we monitor real-time data streams and attempt to match each infant within the HIE to Indiana’s statewide newborn screening registry. A robust matching process is needed because the HIE consists of many different organizations with widely varying types and quality of identifying data suitable for matching. We have implemented a configurable, generalized probabilistic method to perform the matching. We describe the design and implementation of the open-source probabilistic matching tool and review results for matching infant data across multiple organizations.