使用词嵌入神经网络模型测量ICU笔记中的隐含偏差
Julien Cobert1, Hunter Mills2, Albert Lee2
1Anesthesia Service, San Francisco VA Health Care System, University of California, San Francisco, San Francisco, CA; Department of Anesthesia and Perioperative Care, University of California, San Francisco, San Francisco, CA.
Chest
|January 10, 2024
概括
在临床笔记中存在隐性偏见,根据地点和时间而异. 自然语言处理 (NLP) 模型可能会延续这些偏见,需要为公平的临床预测制定失智化策略.
科学领域:
- 医疗信息学 医疗信息学
- 自然语言处理自然语言处理.
- 健康差异 在健康上的差异
背景情况:
- 众所周知,非医疗数据集中的类似人类偏差是通过自然语言处理 (NLP) 算法传输的.
- 目前尚不清楚,应用到医疗笔记的NLP算法是否可以类似地传递偏见并加强健康差异.
研究的目的:
- 在临床笔记中识别隐含偏见.
- 为了确定这些偏差是否在不同的时间段和地理位置上是稳定的.
主要方法:
- 使用无监督的文字嵌入算法来定量测量上下文相似性.
- 分析了加利福尼亚大学旧金山分校 (2012-2022) 和伯特以色列院士医院 (2001-2012) 的重症监护室笔记.
- 评估了种族/种族描述符和污名化语言 (例如,不合作,暴力) 之间的上下文相似性.
主要成果:
- 在UCSF的笔记中,黑人描述词与白人描述词相比,对"暴力"词的上下文相似性较小.
- 相反,在BIDMC的注释中,与白人描述词相比,黑人描述词与"暴力"词的上下文相似性更大.
- UCSF的数据还表明,黑人描述词比拉丁语描述词更类似于"被动"和"不合规"的词.
结论:
- 隐性偏见可以在重症监护室 (ICU) 笔记中检测到.
- 种族/民族描述词和污名化语言之间的上下文关系因时间和地点而异.
- 在临床数据上训练的NLP模型可能会传递隐含的偏见,可能会加强健康差异;积极的 debiasing 对于临床预测中的算法公平性至关重要.
相关概念视频
Stereotypes, Prejudice, and Discrimination
90.2K
Humans are very diverse and although we share many similarities, we also have many differences. The social groups we belong to help form our identities (Tajfel, 1974). These differences may be difficult for some people to reconcile, which may lead to prejudice toward people who are different. Prejudice is a negative attitude and feeling toward an individual based solely on one’s membership in a particular social group (Allport, 1954; Brown, 2010). Prejudice is common against people who...
90.2K
Stereotype Content Model
14.7K
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...
14.7K
Bias
4.2K
Bias refers to any tendency that prevents a question from being considered unprejudiced. In research, bias occurs when one outcome or answer is selected or encouraged over others in sampling or testing. Bias can occur during any research phase, including study design, data collection, analysis, and publication.
In statistics, a sampling bias is created when a sample is collected from a population, and some members of the population are not as likely to be chosen as others (remember, each member...
In statistics, a sampling bias is created when a sample is collected from a population, and some members of the population are not as likely to be chosen as others (remember, each member...
4.2K


