大型语言模型揭示了发作结果的差异
Kevin Xie1,2, William K S Ojemann1,2, Ryan S Gallagher2,3
1Department of Bioengineering, University of Pennsylvania, Philadelphia, PA 19104, United States.
概括
大语言模型 (LLM) 显示在治疗中没有内在偏差. 然而,LLM分析显示,根据性别,保险和收入,发作结果存在差异,突出了公平护的需要.
科学领域:
- 医疗信息学 医疗信息学
- 神经学 神经学
- 医疗保健服务研究 医疗服务研究
背景情况:
- 大语言模型 (LLM) 为医疗保健转型提供了潜力,但可能会延续或引入偏见.
- 健康的社会决定因素影响了治疗的准入,但它们对获得治疗的人群中发作结果的影响尚不清楚.
研究的目的:
- 为了评估特定的LLM在人口群体内内在的偏见.
- 用LLM提取的数据来确定人口因素是否与不同的发作结果有关.
主要方法:
- 一个针对的LLM被评估为跨种族,种族,性别,收入和保险状况的预测准确性和信心.
- 从84,675次诊所访问 (25,612名患者) 中,LLM分类的发作自由度被使用单变量和多变量模型分析,以确定结果差异.
主要成果:
- 该LLM在人口统计组的预测准确性或信心方面表现出最小的偏差.
- 多变量分析显示,女性 (OR 1.33),公共保险患者 (OR 1.53) 和来自低收入邮政编码 (OR ≥1.22) 的个人发作结果更差.
- 与白人患者相比,黑人患者在单变量但不是多变量分析中表现较差.
结论:
- 特定于的LLM没有表现出对人口群体的重大内在偏见.
- 在LLM的分析中,发现了与性别,保险状况和社会经济因素相关的扣押结果的显著差异.
- 这些发现强调了迫切需要解决和减少治疗中的健康差异.
相关概念视频
01:27Language and Cognition
345
Language serves as a bridge between ideas and communication, influencing how individuals perceive and interact with the world. Psychologists have long debated whether language shapes thought or vice versa. This discussion gained grip with Edward Sapir and Benjamin Lee Whorf in the 1940s, who proposed that language determines thought, a concept known as linguistic determinism. They suggested that the vocabulary and structure of a language influence how its speakers think and perceive reality.
345
01:28Lateralization
330
Brain lateralization refers to the division of mental processes and functions between the two hemispheres of the brain, a phenomenon that optimizes neural efficiency and underpins complex abilities in humans. This specialization allows each hemisphere to perform tasks where it has a comparative advantage, facilitating more refined cognitive capabilities across different domains.
330