中国大型语言模型在医疗保健中延续社会偏见的潜力:一个模型评估研究
Chenxi Liu1, Jianing Zheng1, Yushu Liu1
1School of Medicine and Health Management, Tongji Medical College, Huazhong University of Science and Technology, 13 Hangkong Road, Wuhan, Hubei, 430030, China.
中国的大型语言模型 (LLM) 显示出社会偏见,过度代表了一些患者群体,并显示了诊断和治疗建议的差异. 对这些人工智能工具的持续评估对于公平的医疗保健至关重要.
科学领域:
- 人工智能在医学中的应用
- 临床信息学 临床信息学
- 健康 公平 卫生 公平
背景情况:
- 大型语言模型 (LLM) 可能会延续医疗保健中的社会偏见.
- 在中国流行的LLM中评估社会偏见对于临床应用至关重要.
研究的目的:
- 系统地评估三个中国LLM (Qwen,Erine,Baichuan) 的潜在社会偏见.
- 在临床场景中分析与患者的性别,种族,教育,收入和保险状况相关的偏见.
主要方法:
- 在医学教育方面,LLM产生了临床病例 (n=8,289),将分布与国家数据进行比较.
- 临床诊断师为临床细节 (n=45,600) 制作了差异诊断和治疗计划.
- 临床医学师评估了患者的需求 (n=51,039),以确定隐含的偏见.
主要成果:
- 这三个LLM都在医学教育,诊断和需求评估方面表现出社会偏见.
- 对性别,种族,收入和保险状况的偏见更为突出.
- 在LLM中,男性,高学历和高收入人群占比过高,少数民族和无保险/低收入患者的转诊率更高.
结论:
- 调查结果显示,中国LLM中存在重大社会偏见,影响了患者代表和护理建议.
- 迫切需要在临床环境中对LLM偏见进行系统和持续的评估,以确保公平和公平.
更多相关视频
05:47Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
Published on: June 13, 2025
05:56Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
Published on: April 14, 2023
相关概念视频
Barriers to Effective Communication II
Cultural barriers:
Differences in values, beliefs, religion, knowledge, and tradition can significantly impact communication. Awareness of nonverbal cues is critical, especially when conversing with a patient from a different culture. What appears appropriate in one culture may be inappropriate in another.
Semantic barriers:
As a result of their tendency to use...
Bias in Epidemiological Studies
Stereotype Content Model
Models of Health Promotion and Illness Prevention I
The health belief model (HBM) attempts to predict health-related behavior in specific belief patterns. According to the HBM, a person's...
Stereotypes, Prejudice, and Discrimination
Language and Cognition
