Imputing Missing Race/Ethnicity in Pediatric Electronic Health Records: Reducing Bias with Use of U.S. Census Location and Surname Data. (11th March 2015)

• Record Type: Journal Article
• Authors: Grundmeier, Robert W.; Song, Lihai; Ramos, Mark J.; Fiks, Alexander G.; Elliott, Marc N.; Fremont, Allen; Pace, Wilson; Wasserman, Richard C.; Localio, Russell
• Is Part Of: Health services research. Volume 50:Number 4(2015)
• Page Start: 946
• Page End: 960
• Publication Date: 2015-03-11
• Subjects: Medical care -- Periodicals; Medical care -- Evaluation -- Periodicals; Hospital care -- Periodicals; Health services administration -- Periodicals; 362
• DOI: 10.1111/1475-6773.12295
• Languages: English
• ISSNs: 0017-9124

Abstract

<abstract abstract-type="main" id="hesr12295-abs-0001"> <title> <x xml:space="preserve">Abstract</x> </title> <sec id="hesr12295-sec-0001" sec-type="section"> <title>Objective</title> <p>To assess the utility of imputing race/ethnicity using U.S. Census race/ethnicity, residential address, and surname information compared to standard missing data methods in a pediatric cohort.</p> </sec> <sec id="hesr12295-sec-0002" sec-type="section"> <title>Data Sources/Study Setting</title> <p>Electronic health record data from 30 pediatric practices with known race/ethnicity.</p> </sec> <sec id="hesr12295-sec-0003" sec-type="section"> <title>Study Design</title> <p>In a simulation experiment, we constructed dichotomous and continuous outcomes with pre‐specified associations with known race/ethnicity. Bias was introduced by nonrandomly setting race/ethnicity to missing. We compared typical methods for handling missing race/ethnicity (multiple imputation alone with clinical factors, complete case analysis, indicator variables) to multiple imputation incorporating surname and address information.</p> </sec> <sec id="hesr12295-sec-0004" sec-type="section"> <title>Principal Findings</title> <p>Imputation using U.S. Census information reduced bias for both continuous and dichotomous outcomes.</p> </sec> <sec id="hesr12295-sec-0005" sec-type="section"> <title>Conclusions</title> <p>The new method reduces bias when race/ethnicity is partially, nonrandomly missing.</p> </sec> </abstract>