Applying Natural Language Processing to Address Healthcare Bias: Using CARE-SD to Evaluate the Distribution of Stigmatizing Language in Clinical Notes

Electronic health records (EHRs) are a critical medium through which patient stigmatization is perpetuated among healthcare teams. We identified doubt markers and stigmatizing labels in MIMIC-III, a de-identified EHR, via expanded lexicon matching and machine learning classifiers. Predictors of rates of linguistic features were assessed using Poisson models. We found higher rates of stigmatizing labels per chart among patients who were Black or African American (RR: 1.16), patients with Medicare/Medicaid or government-run insurance (RR: 2.46), self-pay (RR: 2.12), and patients with a variety of stigmatizing disease and mental health conditions (RR: 1.50–4.90). Patterns among doubt markers were similar, though male patients had higher rates of doubt markers (RR: 1.25). We found increased stigmatizing labels used by nurses (RR: 1.40), and social workers (RR: 2.25), with similar patterns of doubt markers. Stigmatizing language occurred at higher rates among historically stigmatized patients, perpetuated by multiple provider types.