SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.14815 · 2024

Demographic Bias of Expert-Level Vision-Language Foundation Models in Medical Imaging

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

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.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2402.14815")
get_code_for_paper("2402.14815")
have("2402.14815")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2402.14815.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2402.14815.svg)](https://syntology.ai/paper/2402.14815)

Connect an agent — have() is free.