Biases in Race and Ethnicity Introduced by Filtering Electronic Health Records for’Complete Data’

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. In this study, we examined the race/ethnicity biases introduced by applying common filters to four clinical records databases.

Recommended citation: Biases in Race and Ethnicity Introduced by Filtering Electronic Health Records for ‘Complete Data’ Jose M. Acitores Cortina, Yasaman Fatapour, Michael Zietz, Kathleen LaRow Brown, Undina Gisladottir, Danner Peter, Oliver John Bear Don’t Walk IV, Aditi Kuchi, Apoorva Srinivasan, Hongyu Liu, Jacob Berkowitz, Kevin Tsang, Nadine Friedrich, Sophia Kievelson, Nicholas P. Tatonetti medRxiv 2024.10.04.24314914; doi: https://doi.org/10.1101/2024.10.04.24314914
Read paper | Download paper