Unmasking and Quantifying Racial Bias of Large Language Models in Medical Report Generation
This research addresses a critical fairness issue in healthcare AI, highlighting biases that could affect medical outcomes for diverse patient groups, though it is incremental as it builds on prior concerns about model biases.
The study tackled the problem of racial bias in large language models like GPT-3.5-turbo and GPT-4 when generating medical reports, finding that these models project higher costs and longer hospitalizations for White populations and show optimistic survival rates in challenging scenarios, mirroring real-world healthcare disparities.
Large language models like GPT-3.5-turbo and GPT-4 hold promise for healthcare professionals, but they may inadvertently inherit biases during their training, potentially affecting their utility in medical applications. Despite few attempts in the past, the precise impact and extent of these biases remain uncertain. Through both qualitative and quantitative analyses, we find that these models tend to project higher costs and longer hospitalizations for White populations and exhibit optimistic views in challenging medical scenarios with much higher survival rates. These biases, which mirror real-world healthcare disparities, are evident in the generation of patient backgrounds, the association of specific diseases with certain races, and disparities in treatment recommendations, etc. Our findings underscore the critical need for future research to address and mitigate biases in language models, especially in critical healthcare applications, to ensure fair and accurate outcomes for all patients.