@article{ref1,
title="Linking mothers and infants within electronic health records: a comparison of deterministic and probabilistic algorithms",
journal="Pharmacoepidemiology and drug safety",
year="2014",
author="Baldwin, Eric and Johnson, Karin and Berthoud, Heidi and Dublin, Sascha",
volume="24",
number="1",
pages="45-51",
abstract="PURPOSE: To compare probabilistic and deterministic algorithms for linking mothers and infants within electronic health records (EHRs) to support pregnancy outcomes research. <br><br>METHODS: The study population was women enrolled in Group Health (Washington State, USA) delivering a liveborn infant from 2001 through 2008 (N = 33 093 deliveries) and infant members born in these years. We linked women to infants by surname, address, and dates of birth and delivery using deterministic and probabilistic algorithms. In a subset previously linked using &quot;gold standard&quot; identifiers (N = 14 449), we assessed each approach's sensitivity and positive predictive value (PPV). For deliveries with no &quot;gold standard&quot; linkage (N = 18 644), we compared the algorithms' linkage proportions. We repeated our analyses in an independent test set of deliveries from 2009 through 2013. We reviewed medical records to validate a sample of pairs apparently linked by one algorithm but not the other (N = 51 or 1.4% of discordant pairs). <br><br>RESULTS: In the 2001-2008 &quot;gold standard&quot; population, the probabilistic algorithm's sensitivity was 84.1% (95% CI, 83.5-84.7) and PPV 99.3% (99.1-99.4), while the deterministic algorithm had sensitivity 74.5% (73.8-75.2) and PPV 95.7% (95.4-96.0). In the test set, the probabilistic algorithm again had higher sensitivity and PPV. For deliveries in 2001-2008 with no &quot;gold standard&quot; linkage, the probabilistic algorithm found matched infants for 58.3% and the deterministic algorithm, 52.8%. On medical record review, 100% of linked pairs appeared valid. <br><br>CONCLUSIONS: A probabilistic algorithm improved linkage proportion and accuracy compared to a deterministic algorithm. Better linkage methods can increase the value of EHRs for pregnancy outcomes research. Copyright © 2014 John Wiley & Sons, Ltd.<p /> <p>Language: en</p>",
language="en",
issn="1053-8569",
doi="10.1002/pds.3728",
url="http://dx.doi.org/10.1002/pds.3728"
}