Medical imaging models have been shown to encode information about patient demographics (age, race, sex) in their latent representation, raising concerns about their potential for discrimination. Here, we ask whether it is feasible and desirable to train models that do not encode demographic attributes. We consider different types of invariance with respect to demographic attributes - marginal, class-conditional, and counterfactual model invariance - and lay out their equivalence to standard notions of algorithmic fairness. Drawing on existing theory, we find that marginal and class-conditional invariance can be considered overly restrictive approaches for achieving certain fairness notions, resulting in significant predictive performance losses. Concerning counterfactual model invariance, we note that defining medical image counterfactuals with respect to demographic attributes is fraught with complexities. Finally, we posit that demographic encoding may even be considered advantageous if it enables learning a task-specific encoding of demographic features that does not rely on human-constructed categories such as 'race' and 'gender'. We conclude that medical imaging models may need to encode demographic attributes, lending further urgency to calls for comprehensive model fairness assessments in terms of predictive performance.

翻译：医学影像模型已被证明会在其潜在表征中编码患者人口统计信息（年龄、种族、性别），这引发了对其潜在歧视风险的担忧。本文探讨训练不编码人口统计属性的模型是否可行且可取。我们考虑针对人口统计属性的三种不同不变性类型——边缘不变性、类别条件不变性和反事实模型不变性——并阐明它们与标准算法公平性概念的等价关系。基于现有理论，我们发现边缘不变性和类别条件不变性在实现特定公平性概念时可被视为过度约束的方法，会导致显著的预测性能损失。对于反事实模型不变性，我们指出定义针对人口统计属性的医学影像反事实存在诸多复杂性。最后，我们认为人口统计编码甚至可能具有优势，因为它能够学习不依赖于人类构建的类别（如“种族”和“性别”）的任务特定人口统计特征编码。我们得出结论：医学影像模型可能需要编码人口统计属性，这进一步强化了从预测性能角度进行全面模型公平性评估的紧迫性。