Demographic Bias of Expert-Level Vision-Language Foundation Models in Medical Imaging
Abstract
Advances in artificial intelligence (AI) have achieved expert-level performance in medical imaging applications. Notably, self-supervised vision-language foundation models can detect a broad spectrum of pathologies without relying on explicit training annotations. However, it is crucial to ensure that these AI models do not mirror or amplify human biases, thereby disadvantaging historically marginalized groups such as females or Black patients. The manifestation of such biases could systematically delay essential medical care for certain patient subgroups. In this study, we investigate the algorithmic fairness of state-of-the-art vision-language foundation models in chest X-ray diagnosis across five globally-sourced datasets. Our findings reveal that compared to board-certified radiologists, these foundation models consistently underdiagnose marginalized groups, with even higher rates seen in intersectional subgroups, such as Black female patients. Such demographic biases present over a wide range of pathologies and demographic attributes. Further analysis of the model embedding uncovers its significant encoding of demographic information. Deploying AI systems with these biases in medical imaging can intensify pre-existing care disparities, posing potential challenges to equitable healthcare access and raising ethical questions about their clinical application.
- Publication:
-
arXiv e-prints
- Pub Date:
- February 2024
- DOI:
- 10.48550/arXiv.2402.14815
- arXiv:
- arXiv:2402.14815
- Bibcode:
- 2024arXiv240214815Y
- Keywords:
-
- Computer Science - Computers and Society;
- Computer Science - Artificial Intelligence;
- Computer Science - Computer Vision and Pattern Recognition;
- Computer Science - Machine Learning
- E-Print:
- Code and data are available at https://github.com/YyzHarry/vlm-fairness