缓解种族和民族偏见,在临床算法中推进健康公平:一个范围审查
Michael P Cary1, Anna Zink2, Sijia Wei3
1Michael P. Cary Jr. (michael.cary@duke.edu), Duke University, Durham, North Carolina.
为了防止医疗保健算法中的歧视,一项审查发现了许多偏见缓解策略,但没有单一的最佳实践. 需要进行进一步的研究,以确定适用于不同临床环境和患者群体的最佳方法.
科学领域:
- 医疗信息学 医疗信息学
- 医疗保健中的人工智能
- 健康 公平 卫生 公平
背景情况:
- 卫生和人类服务部 (HHS) 提出了针对临床算法歧视的规则.
- 缺乏具体的HHS指导方针使医疗保健实体难以遵守.
- 医疗保健算法中的种族和种族偏见是一个重大问题.
研究的目的:
- 识别和审查减轻临床算法偏差的策略.
- 关注医疗保健应用中的种族和种族偏见.
- 分析现有的关于偏见识别和缓解工具的文献.
主要方法:
- 进行了从2011年到2022年的文献范围审查.
- 包括109篇文章:45个实证应用,16个框架,48个评论/观点.
- 专注于在临床决策算法中识别偏差缓解策略.
主要成果:
- 确定了各种各样的技术,运营和全系统偏差缓解策略.
- 没有找到关于减轻偏见的单一最佳实践的共识.
- 突出了评估算法偏差的各种工具和框架.
结论:
- 现有的策略提供了各种方法来缓解临床算法的偏差.
- 进一步的研究对于建立最佳的,特定于环境的偏差缓解方法至关重要.
- 解决医疗保健算法的偏见需要根据特定因素定制的解决方案.
更多相关视频
06:55Inverse Probability of Treatment Weighting Propensity Score using the Military Health System Data Repository and National Death Index
Published on: January 8, 2020
07:31Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
相关概念视频
Bias in Epidemiological Studies
Strategies for Assessing and Addressing Confounding
Confounding can be addressed at both the design phase of a study and through analytical methods after data...
Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast,...
Bias
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...
Ethical Issues
Ethical Concerns in Healthcare:
Stereotypes, Prejudice, and Discrimination
