CheXclusion: Fairness gaps in deep chest X-ray classifiers

Machine learning systems have received much attention recently for their ability to achieve expert-level performance on clinical tasks, particularly in medical imaging. Here, we examine the extent to which state-of-the-art deep learning classifiers trained to yield diagnostic labels from X-ray images are biased with respect to protected attributes. We train convolution neural networks to predict 14 diagnostic labels in 3 prominent public chest X-ray datasets: MIMIC-CXR, Chest-Xray8, CheXpert, as well as a multi-site aggregation of all those datasets. We evaluate the TPR disparity -- the difference in true positive rates (TPR) -- among different protected attributes such as patient sex, age, race, and insurance type as a proxy for socioeconomic status. We demonstrate that TPR disparities exist in the state-of-the-art classifiers in all datasets, for all clinical tasks, and all subgroups. A multi-source dataset corresponds to the smallest disparities, suggesting one way to reduce bias. We find that TPR disparities are not significantly correlated with a subgroup's proportional disease burden. As clinical models move from papers to products, we encourage clinical decision makers to carefully audit for algorithmic disparities prior to deployment. Our code can be found at,

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Multi-Label Classification ChestX-ray14 DensNet121 Average AUC on 14 label 84.9 # 1
Multi-Label Classification CheXpert DensNet121 AVERAGE AUC ON 14 LABEL 0.805 # 205
Multi-Label Classification MIMIC-CXR DensNet121 Average AUC on 14 label 0.8340000000000001 # 1