Biases in Race and Ethnicity Introduced by Filtering Electronic Health Records for “Complete Data”: Observational Clinical Data Analysis
JMIR Medical Informatics · 2025
DOI: 10.2196/67591 ↗Kurz gefasst
Fachartikel in der Zeitschrift JMIR Medical Informatics, 2025. Verfasst von Jose Miguel Acitores Cortina und 14 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computational Biomedicine, Cedars-Sinai Medical Center, 700 North San Vicente Boulevard, Pacific Design Center Suite G540, Los Angeles,…. Hauptthemen laut MEDLINE: Electronic Health Records, Ethnicity, Racial Groups. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NLM NIH HHS, NHLBI NIH HHS.
Abstract (Originalsprache)
Background
Integrated clinical databases from national biobanks have advanced the capacity for disease research. Data quality and completeness filters are used when building clinical cohorts to address limitations of data missingness. However, these filters may unintentionally introduce systemic biases when they are correlated with race and ethnicity.
Objective
In this study, we examined the race and ethnicity biases introduced by applying common filters to 4 clinical records databases. Specifically, we evaluated whether these filters introduce biases that disproportionately exclude minoritized groups.
Methods
We applied 19 commonly used data filters to electronic health record datasets from 4 geographically varied locations comprising close to 12 million patients to understand how using these filters introduces sample bias along racial and ethnic groupings. These filters covered a range of information, including demographics, medication records, visit details, and observation periods. We observed the variation in sample drop-off between self-reported ethnic and racial groups for each site as we applied each filter individually.
Results
Applying the observation period filter substantially reduced data availability across all races and ethnicities in all 4 datasets. However, among those examined, the availability of data in the white group remained consistently higher compared to other racial groups after applying each filter. Conversely, the Black or African American group was the most impacted by each filter on these 3 datasets: Cedars-Sinai dataset, UK Biobank, and Columbia University dataset. Among the 4 distinct datasets, only applying the filters to the All of Us dataset resulted in minimal deviation from the baseline, with most racial and ethnic groups following a similar pattern.
Conclusions
Our findings underscore the importance of using only necessary filters, as they might disproportionally affect data availability of minoritized racial and ethnic populations. Researchers must consider these unintentional biases when performing data-driven research and explore techniques to minimize the impact of these filters, such as probabilistic methods or adjusted cohort selection methods. Additionally, we recommend disclosing sample sizes for racial and ethnic groups both before and after data filters are applied to aid the reader in understanding the generalizability of the results. Future work should focus on exploring the effects of filters on downstream analyses.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Computational Biomedicine, Cedars-Sinai Medical Center, 700 North San Vicente Boulevard, Pacific Design Center Suite G540, Los Angeles, CA, 90069, United States, 1 424 315 1031.
- Cedars-Sinai Cancer, Cedars-Sinai Medical Center, Los Angeles, CA, United States.
- Department of Systems Biology, Columbia University, New York, NY, United States.
- Department of Biomedical Informatics, Columbia University, New York, NY, United States.
- Department of Biomedical Informatics and Medical Education, University of Washington, Seattle, WA, United States.
ORCID-Profile: Jose Miguel Acitores Cortina, Yasaman Fatapour, Kathleen LaRow Brown, Undina Gisladottir, Michael Zietz, Oliver John Bear Don't Walk Iv, Danner Peter, Jacob S Berkowitz, Nadine A Friedrich, Sophia Kivelson, Aditi Kuchi, Hongyu Liu, Apoorva Srinivasan, Kevin K Tsang, Nicholas P Tatonetti
Förderung
- NLM NIH HHS
- NHLBI NIH HHS
Zitieren
APA
Acitores Cortina, J. M., Fatapour, Y., Brown, K. L., Gisladottir, U., Zietz, M., Bear Don't Walk Iv, O. J., Peter, D., Berkowitz, J. S., Friedrich, N. A., Kivelson, S., Kuchi, A., Liu, H., Srinivasan, A., Tsang, K. K., & Tatonetti, N. P. (2025). Biases in Race and Ethnicity Introduced by Filtering Electronic Health Records for “Complete Data”: Observational Clinical Data Analysis. JMIR Medical Informatics. https://doi.org/10.2196/67591
Vancouver
Acitores Cortina JM, Fatapour Y, Brown KL, Gisladottir U, Zietz M, Bear Don't Walk Iv OJ, et al. Biases in Race and Ethnicity Introduced by Filtering Electronic Health Records for “Complete Data”: Observational Clinical Data Analysis. JMIR Medical Informatics. 2025. doi:10.2196/67591
BibTeX
@article{AcitoresCortina2025,
author = {Acitores Cortina, Jose Miguel and Fatapour, Yasaman and Brown, Kathleen LaRow and Gisladottir, Undina and Zietz, Michael and Bear Don't Walk Iv, Oliver John and Peter, Danner and Berkowitz, Jacob S and Friedrich, Nadine A and Kivelson, Sophia and Kuchi, Aditi and Liu, Hongyu and Srinivasan, Apoorva and Tsang, Kevin K and Tatonetti, Nicholas P},
title = {Biases in Race and Ethnicity Introduced by Filtering Electronic Health Records for “Complete Data”: Observational Clinical Data Analysis},
journal = {JMIR Medical Informatics},
year = {2025},
doi = {10.2196/67591}
}
EUVIMED