News: Implicit bias exists in EHR notes, study finds
A study published by Health Affairs found that Black patients were 2.54 times more likely to have negative descriptors in the EHR notes compared to white patients. The study sampled history and physical notes from 18,459 patients and analyzed for sentences containing negative descriptions of the patient or their behavior, including “resistant” or “noncompliant.”
The study notes that while the above terms and similar descriptors are not explicitly stigmatizing terms, they may still provide a negative connotation with the patient. The findings are especially alarming as patient histories and EHR notes are often transferred to and seen by other providers.
“Negative descriptors written in the admission history and physical may be likely to be copied into subsequent notes, recommunicating and amplifying potential biases,” the study notes. “This practice underscores the responsibility of providers who document the initial patient encounter to do so in an aware and sensitive manner.”
Subsequent providers may read and then perpetuate negative descriptors in the EHR, further reinforcing stigmas to others in the healthcare team.
Additionally, the study found that notes written after the start of the COVID-19 pandemic were less likely to have a negative descriptor. This is likely due to the start of the pandemic coinciding with the Black Lives Matter movement in response to racialized violence, as well as the pandemic shedding light on racial health disparities.
“These social pressures may have sensitized providers to racism and increased empathy for the experiences of racially minoritized communities,” the study notes. “Additional investigation may use a similar machine learning approach to examine EHR data over a longer period of time for repeated use of negative descriptors and for potential effects on health outcomes.”
Editor’s note: The Health Affairs published study can be found here. Additional ACDIS coverage of health disparities in minority groups can be found here.