A new study of patient electronic health records found that doctors are more likely to use negative language when describing visits to black and Hispanic patients than to white patients, which researchers say could lead to bias and unequal treatment of patients.

The study entitled “Investigating linguistic differences in electronic health records for different patients with diabetes: Natural language processing analysis” was published in JMIR Medical Informaticsanalyzed the medical records of black, white, and Hispanic or Latino patients seen by 281 physicians in a large metropolitan area. The researchers were interested in whether or not physicians showed bias in word choice when describing patients in post-visit reports.

“Previous studies have shown that nurses’ biases may be part of the cause of racial health disparities,” said Eden King, Lynette S. Autrey Professor of Psychology at Rice University and one of the study’s lead authors. “We wanted to know if we could detect such biases in the language nurses use in their medical records, and we did.”

Physician summaries of black and Hispanic patients contained significantly more negative adjectives (such as “unfriendly,” “negative,” or “stupid”) and significantly more fear and disgust words (such as “intimidate,” “attack,” “cringe,” and “criticize”) than did the summaries of white, non-Hispanic patients.

The notes of Hispanic or Latino patients contained significantly fewer positive adjectives (such as “supportive,” “friendly,” “great,” and “nice”), trust verbs (such as “affirm,” “advise,” “entrust,” and “cooperate”), and joy words (such as “admiration,” “excited,” “glad,” and “pleased”) than the notes of white, non-Hispanic patients.

“Understanding that doctors’ language can indicate bias provides an opportunity to interrupt it,” King said. “If we can perfect algorithms to detect such bias, we can raise awareness in the moment of the patient-doctor conversation. That awareness could be enough to promote more equitable health care.”

King and her colleagues hope their work will enable physicians and other researchers to identify and mitigate bias in the medical treatment of people, with the goal of reducing health disparities caused by bias.