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.

我们研究深度分类器中的性能差异。我们发现分类器将个体分为子群的能力在医学成像模态和保护特性之间存在显著差异；关键是，我们展示了这一特性对算法偏见具有预测作用。通过理论分析和广泛的经验评估，我们发现了子群分离性、子群差异和在训练数据存在系统偏差（如低诊断率）时性能下降之间的关系。我们的发现为理解模型如何变得有偏提供了新的视角，为公平的医学成像人工智能的发展提供了重要的见解。