A new study led by Eden King, professor at Rice University, has uncovered significant racial disparities in the language physicians use in electronic health records (EHRs). The research analyzed EHRs of Black, white, and Hispanic or Latino patients treated by 281 doctors in a major metropolitan area.
Using advanced natural language processing, the study found that notes for Black and Hispanic or Latino patients contained more negative adjectives like “unkind” and “stupid,” as well as words associated with fear and disgust. In contrast, records for white patients featured more positive language, including words like “supportive” and “kind.”
“Language and communication are central to social interactions across cultures, including the critical exchanges that occur between clinicians and patients,” King stated. “Our study sought to uncover whether the words physicians use in health records reflect biases, and the results are concerning.”
These findings align with previous research showing that racial and ethnic minorities often receive inferior care, marked by less empathy and reduced rapport. The 2018 National Healthcare Disparities Report found that Black and Hispanic patients frequently experience worse care on numerous quality measures compared to white patients.
The implications of these linguistic biases are significant, as EHRs influence future medical decisions. The study’s authors emphasize that addressing these biases is crucial for improving health outcomes for minority populations. King suggests developing algorithms to detect biases and raise awareness among clinicians during patient interactions.
This research underscores the need for systemic changes in medical training and EHR utilization to recognize and mitigate unconscious biases, potentially leading to more equitable healthcare for all patients.
See “New Study Uncovers Racial Bias In Language Used By Physicians In Medical Records” (August 15, 2024)
