2023/07/06 by Charles Jones, Mélanie Roschewitz, Jones, Charles +3 · 2 citations
Medicine · Environmental Science · #COVID-19 and healthcare impacts #Climate Change and Health Impacts #Artificial Intelligence in Healthcare and Education
paper · pdf · doi:10.48550/arxiv.2307.02791
We investigate performance disparities in deep classifiers. We find that the ability of classifiers to separate individuals into subgroups varies substantially across medical imaging modalities and protected characteristics; crucially, we show that this property is predictive of algorithmic bias. Through theoretical analysis and extensive empirical evaluation, we find a relationship between subgroup separability, subgroup disparities, and performance degradation when models are trained on data with systematic bias such as underdiagnosis. Our findings shed new light on the question of how models become biased, providing important insights for the development of fair medical imaging AI.