In this work, we examine the extent to which embeddings may encode marginalized populations differently, and how this may lead to a perpetuation of biases and worsened performance on clinical tasks. We pretrain deep embedding models (BERT) on medical notes from the MIMIC-III hospital dataset, and quantify potential disparities using two approaches. First, we identify dangerous latent relationships that are captured by the contextual word embeddings using a fill-in-the-blank method with text from real clinical notes and a log probability bias score quantification. Second, we evaluate performance gaps across different definitions of fairness on over 50 downstream clinical prediction tasks that include detection of acute and chronic conditions. We find that classifiers trained from BERT representations exhibit statistically significant differences in performance, often favoring the majority group with regards to gender, language, ethnicity, and insurance status. Finally, we explore shortcomings of using adversarial debiasing to obfuscate subgroup information in contextual word embeddings, and recommend best practices for such deep embedding models in clinical settings.

本论文研究了嵌入方法在编码社会边缘群体时的偏见问题，以及这种偏见可能导致的临床任务性能下降。通过使用MIMIC-III医院数据集中的医学记录对深度嵌入模型(BERT)进行预训练并使用两种方法量化潜在不公正性，作者发现BERT表征训练出的分类器在性别、语言、族裔和保险等方面表现出明显的性能差异，以及通过对抗去偏差的不足。最后提出了这些问题的最佳实践。

医疗背景下词嵌入的偏见量化