{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T11:13:36Z","timestamp":1769598816623,"version":"3.49.0"},"reference-count":20,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T00:00:00Z","timestamp":1760486400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"name":"Indiana University-Ohio State University Maternal and Pediatric Precision in Therapeutics Data, Model, Knowledge, and Research Coordination Center"},{"DOI":"10.13039\/100000071","name":"NICHD","doi-asserted-by":"publisher","award":["5P30HD106451-04"],"award-info":[{"award-number":["5P30HD106451-04"]}],"id":[{"id":"10.13039\/100000071","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,2,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>We created a probabilistic maternal\u2013child electronic health record (EHR) linkage algorithm to promote clinical research in maternal\u2013child health.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We used EHR data from 1994 to 2024 to create an XGBoost model to predict maternal\u2013child linkages. The model used standard EHR elements as predictor variables, including first name, last name, birthdate, address, phone number, email, and an EHR-embedded maternal\u2013child indicator as the deterministic outcome.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>From 82 million unique records, 6.2 billion potential pairs met blocking criteria. Of the potential pairs, 33\u2009364\u2009674 contained the deterministic indicator and were used as cases, and an equal number of controls were randomly sampled. The final model obtained an accuracy of 92%, a precision of 98%, a recall of 87%, and an F1-score of 92%.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>We derived and validated a probabilistic maternal\u2013child linkage algorithm using routinely collected EHR data elements that could benefit future observational research in maternal\u2013child health.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/jamia\/ocaf177","type":"journal-article","created":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T11:58:27Z","timestamp":1758801507000},"page":"451-456","source":"Crossref","is-referenced-by-count":0,"title":["Derivation and validation of an algorithm for maternal\u2013child linkage in electronic health records"],"prefix":"10.1093","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5251-2399","authenticated-orcid":false,"given":"Colin M","family":"Rogerson","sequence":"first","affiliation":[{"name":"Department of Pediatrics, Indiana University School of Medicine , Indianapolis, IN, 46202,","place":["United States"]},{"name":"Regenstrief Institute , Indianapolis, IN, 46202,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christopher W","family":"Bartlett","sequence":"additional","affiliation":[{"name":"Department of Pediatrics, The Ohio State University , Columbus, OH, 43210,","place":["United States"]},{"name":"Office of Data Sciences, The Steve & Cindy Rasmussen Institute for Genomic Medicine, Abigail Wexner Research Institute, Nationwide Children\u2019s Hospital , Columbus, OH, 43205,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John","family":"Price","sequence":"additional","affiliation":[{"name":"Regenstrief Institute , Indianapolis, IN, 46202,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0746-1809","authenticated-orcid":false,"given":"Lang","family":"Li","sequence":"additional","affiliation":[{"name":"Office of Data Sciences, The Steve & Cindy Rasmussen Institute for Genomic Medicine, Abigail Wexner Research Institute, Nationwide Children\u2019s Hospital , Columbus, OH, 43205,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4297-9221","authenticated-orcid":false,"given":"Eneida A","family":"Mendonca","sequence":"additional","affiliation":[{"name":"Cincinnati Children\u2019s Hospital Medical Center , Cincinnati, OH, 45229,","place":["United States"]},{"name":"Department of Pediatrics, University of Cincinnati , Cincinnati, OH, 45229,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8093-6639","authenticated-orcid":false,"given":"Shaun","family":"Grannis","sequence":"additional","affiliation":[{"name":"Department of Pediatrics, Indiana University School of Medicine , Indianapolis, IN, 46202,","place":["United States"]},{"name":"Regenstrief Institute , Indianapolis, IN, 46202,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2025,10,15]]},"reference":[{"key":"2026012716172413200_ocaf177-B1","doi-asserted-by":"publisher","first-page":"2811","DOI":"10.1016\/s0140-6736(16)00738-8","article-title":"Reproductive, maternal, newborn, and child health: key messages from Disease Control Priorities 3rd Edition","volume":"388","author":"Black","year":"2016","journal-title":"Lancet"},{"key":"2026012716172413200_ocaf177-B2","doi-asserted-by":"publisher","first-page":"657","DOI":"10.1136\/medethics-2016-103955","article-title":"Vulnerability of pregnant women in clinical research","volume":"43","author":"van der Zande","year":"2017","journal-title":"J Med Ethics"},{"key":"2026012716172413200_ocaf177-B3","doi-asserted-by":"publisher","first-page":"e222656","DOI":"10.1001\/jamahealthforum.2022.2656","article-title":"Protecting the privacy of reproductive health information after the fall of Roe v Wade","volume":"3","author":"Spector-Bagdady","year":"2022","journal-title":"JAMA Health Forum"},{"key":"2026012716172413200_ocaf177-B4","first-page":"421","article-title":"Duplicate medical records: a survey of Twin Cities healthcare organizations","volume":"2009","author":"McClellan","year":"2009","journal-title":"AMIA Annu Symp Proc"},{"key":"2026012716172413200_ocaf177-B5","doi-asserted-by":"publisher","first-page":"e665","DOI":"10.1097\/pts.0000000000000434","article-title":"Reducing and sustaining duplicate medical record creation by usability testing and system redesign","volume":"17","author":"Khunlertkit","year":"2021","journal-title":"J Patient Saf"},{"key":"2026012716172413200_ocaf177-B6","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1136\/bmjqs-2012-001419","article-title":"Matching identifiers in electronic health records: implications for duplicate records and patient safety","volume":"22","author":"McCoy","year":"2013","journal-title":"BMJ Qual Saf"},{"key":"2026012716172413200_ocaf177-B7","doi-asserted-by":"publisher","first-page":"350","DOI":"10.3233\/shti200567","article-title":"Rules based data quality assessment on claims database","volume":"272","author":"Gadde","year":"2020","journal-title":"Stud Health Technol Inform"},{"key":"2026012716172413200_ocaf177-B8","doi-asserted-by":"publisher","first-page":"ooae024","DOI":"10.1093\/jamiaopen\/ooae024","article-title":"Diving into CDC pregnancy data in the United States: longitudinal study and interactive application","volume":"7","author":"Clark-Sevilla","year":"2024","journal-title":"JAMIA Open"},{"key":"2026012716172413200_ocaf177-B9","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1093\/jamia\/ocy191","article-title":"Evaluating the effect of data standardization and validation on patient matching accuracy","volume":"26","author":"Grannis","year":"2019","journal-title":"J Am Med Inform Assoc"},{"key":"2026012716172413200_ocaf177-B10","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1177\/0962280215626180","article-title":"Automated linkage of patient records from disparate sources","volume":"27","author":"Li","year":"2018","journal-title":"Stat Methods Med Res"},{"key":"2026012716172413200_ocaf177-B11","doi-asserted-by":"publisher","first-page":"e628","DOI":"10.1097\/pcc.0000000000002380","article-title":"Joining datasets without identifiers: probabilistic linkage of virtual pediatric systems and PEDSnet","volume":"21","author":"Dziorny","year":"2020","journal-title":"Pediatr Crit Care Med"},{"key":"2026012716172413200_ocaf177-B12","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1007\/s40290-020-00371-8","article-title":"Building a data linkage foundation for mother-child pharmacoepidemiology research","volume":"35","author":"Whitmore","year":"2021","journal-title":"Pharmaceut Med"},{"key":"2026012716172413200_ocaf177-B13","doi-asserted-by":"publisher","first-page":"e0164667","DOI":"10.1371\/journal.pone.0164667","article-title":"Linking data for mothers and babies in de-identified electronic health data","volume":"11","author":"Harron","year":"2016","journal-title":"PLoS One"},{"key":"2026012716172413200_ocaf177-B14","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1007\/s10995-013-1236-7","article-title":"Development of a linked perinatal data resource from state administrative and community-based program data","volume":"18","author":"Hall","year":"2014","journal-title":"Matern Child Health J"},{"key":"2026012716172413200_ocaf177-B15","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1186\/s12874-023-02073-6","article-title":"Development and evaluation of an algorithm to link mothers and infants in two US commercial healthcare claims databases for pharmacoepidemiology research","volume":"23","author":"Weaver","year":"2023","journal-title":"BMC Med Res Methodol"},{"key":"2026012716172413200_ocaf177-B16","doi-asserted-by":"crossref","first-page":"S81","DOI":"10.1097\/00124784-200411001-00013","article-title":"The Indiana network for patient care: an integrated clinical information system informed by over thirty years of experience","volume":"10","author":"Biondich","year":"2004","journal-title":"J Public Health Manag Pract"},{"key":"2026012716172413200_ocaf177-B17","doi-asserted-by":"publisher","first-page":"1453","DOI":"10.1016\/s0140-6736(07)61602-x","article-title":"The Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) statement: guidelines for reporting observational studies","volume":"370","author":"von Elm","year":"2007","journal-title":"Lancet"},{"key":"2026012716172413200_ocaf177-B18","first-page":"43","article-title":"Real world performance of approximate string comparators for use in patient matching","volume":"107","author":"Grannis","year":"2004","journal-title":"Stud Health Technol Inform"},{"key":"2026012716172413200_ocaf177-B19","doi-asserted-by":"publisher","first-page":"g7594","DOI":"10.1136\/bmj.g7594","article-title":"Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement","volume":"350","author":"Collins","year":"2015","journal-title":"Bmj"},{"key":"2026012716172413200_ocaf177-B20","author":"Office of the National Coordinator for Health Information Technology","year":"2023"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/33\/2\/451\/64713888\/ocaf177.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/33\/2\/451\/64713888\/ocaf177.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T21:17:34Z","timestamp":1769548654000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/33\/2\/451\/8287206"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,15]]},"references-count":20,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,10,15]]},"published-print":{"date-parts":[[2026,2,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocaf177","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,2]]},"published":{"date-parts":[[2025,10,15]]}}}