机器学习的公平性分析预测了急性精神病治疗中的侵略性
Yifan Wang1,2, Laura Sikstrom1,3, Robert Xiao1
1The Krembil Centre for Neuroinformatics, Centre for Addition and Mental Health, Toronto, ON, Canada.
Npj mental health research
|March 2, 2026
概括
机器学习 (ML) 模型用于预测精神病学中的侵略性显示不公平. 这些算法可能会加剧少数群体现有的健康不平等现象,需要在临床使用前进行公平性检查.
科学领域:
- 精神病学是一个精神病学.
- 计算机科学 计算机科学
- 健康 公平 卫生 公平
背景情况:
- 机器学习 (ML) 用于急性精神病学中的风险评估.
- 机器学习算法可能会基于受保护的特征 (如性别和种族) 显示偏见.
- 关于ML在预测精神病侵略方面的公平性存在有限的研究.
研究的目的:
- 在急性精神病学中调查基于ML的侵略预测的公平性.
- 在患者子组之间识别ML模型表现的差异.
主要方法:
- 在电子健康记录上训练了一种随机森林ML算法 (17,703名患者,42,719个观察日).
- 通过分析假阳性率 (FPR) 和真阳性率 (TPR) 来评估预测公平性.
- 基于种族/种族,性别,入学方式,公民身份和住房状况的评估差异.
主要成果:
- 在ML模型中,ROC-AUC达到0.81.
- 在患者子组中发现了FPR和TPR的显著差异.
- 中东和黑人患者,男性,警察入院患者和住房不稳定的患者观察到更高的FPR.
结论:
- 精神病学风险评估中的ML算法可以延续和放大社会不平等.
- 在临床实施ML工具之前,解决模型公平性至关重要.
- 公平性评估对于确保公平的患者护理至关重要.
相关概念视频
01:30Psychosurgery
Psychosurgery, the surgical alteration or permanent removal of brain tissue to alleviate severe psychological conditions, stands as one of the most radical and controversial treatments in the history of mental health care. Its development and application have evolved significantly, marked by dramatic shifts in scientific understanding and ethical perspectives.
Historical Development of Psychosurgery
In the 1930s, Portuguese neurologist Antonio Egas Moniz introduced a surgical procedure designed...
Historical Development of Psychosurgery
In the 1930s, Portuguese neurologist Antonio Egas Moniz introduced a surgical procedure designed...
01:29Dark Triad and Person Perception
Person perception is influenced by both external behaviors and the observer’s internal characteristics, including personality traits. Individuals with dark personality traits, comprising psychopathy, Machiavellianism, and narcissism — collectively known as the dark triad – exhibit manipulative and exploitative tendencies in social contexts. These traits affect how they perceive others and how they are perceived.The Role of Dark Personality Traits in Person PerceptionBlack et al. (2014) explored...