Abstract
<jats:p> Stigmatizing language in medical documentation may reflect and perpetuate bias, but its prevalence in obstetrics has not been systematically quantified. We applied a keyword-guided BERT classifier to 640,345 obstetric notes from 26,178 pregnancies at an academic medical center. Stigmatizing language was detected in 47% of 26,178 pregnancies. Black pregnancies had significantly higher odds of stigmatizing language compared with Asian (aOR=1.5, p=3x10 <jats:sup>-8</jats:sup> ) or White (aOR=1.4, p=6x10 <jats:sup>-6</jats:sup> ). Indicated and spontaneous preterm births were also significantly associated with stigmatizing language compared to term (aORs=1.5, 1.2; p=7x10 <jats:sup>-12</jats:sup> , 0.01). Pregnant individuals with only 12th-grade maternal education were more likely to experience stigma than those with college (aOR=1.5; p=4x10 <jats:sup>-14</jats:sup> ). These findings provide evidence of differences in clinical documentation across race, education levels, and clinical conditions. They also demonstrate how automated natural language processing can enable systematic monitoring of bias in healthcare language at scale. </jats:p>