English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Recent breakthroughs in large language models (LLMs) have led to their rapiddissemination and widespread use. One early application has been to medicine,where LLMs have been investigated to streamline clinical workflows andfacilitate clinical analysis and decision-making. However, a leading barrier tothe deployment of Artificial Intelligence (AI) and in particular LLMs has beenconcern for embedded gender and racial biases. Here, we evaluate whether aleading LLM, ChatGPT 3.5, exhibits gender and racial bias in clinicalmanagement of acute coronary syndrome (ACS). We find that specifying patientsas female, African American, or Hispanic resulted in a decrease in guidelinerecommended medical management, diagnosis, and symptom management of ACS. Mostnotably, the largest disparities were seen in the recommendation of coronaryangiography or stress testing for the diagnosis and further intervention of ACSand recommendation of high intensity statins. These disparities correlate withbiases that have been observed clinically and have been implicated in thedifferential gender and racial morbidity and mortality outcomes of ACS andcoronary artery disease. Furthermore, we find that the largest disparities areseen during unstable angina, where fewer explicit clinical guidelines exist.Finally, we find that through asking ChatGPT 3.5 to explain its reasoning priorto providing an answer, we are able to improve clinical accuracy and mitigateinstances of gender and racial biases. This is among the first studies todemonstrate that the gender and racial biases that LLMs exhibit do in factaffect clinical management. Additionally, we demonstrate that existingstrategies that improve LLM performance not only improve LLM performance inclinical management, but can also be used to mitigate gender and racial biases.

ChatGPT Exhibits Gender and Racial Biases in Acute Coronary Syndrome Management