大脑年龄算法性能中的种族和种族差异:通过六种流行的方法调查偏差
Dorthea J Adkins1, Jamie L Hanson1,2
1Learning, Research & Development Center, University of Pittsburgh, Pittsburgh, PA USA.
medRxiv : the preprint server for health sciences
|September 26, 2025
概括
大脑年龄算法显示了种族群体之间的性能差异,非洲裔美国人和西班牙裔美国人的准确性降低了. 这凸显了包容性发展的必要性,以防止神经成像生物标志物的健康差异.
科学领域:
- 神经成像是一种神经成像.
- 生物标志物 生物标志物
- 健康差异 在健康上的差异
背景情况:
- 大脑年龄算法通过神经成像数据估计生物衰老.
- 当前的算法往往缺乏种族和民族的多样性,风险偏见.
- 算法偏差可能会加剧现有的健康差异.
研究的目的:
- 为了评估6个流行的大脑年龄算法在不同种族和种族群体的表现.
- 识别与种族和种族有关的大脑年龄估计中的潜在偏差.
- 评估这些偏差对临床实用性的影响.
主要方法:
- 利用了来自健康和衰老大脑研究-健康差异 (HABS-HD) 的数据,其中包括1,123名白人,1,107名西班牙裔和678名非洲裔美国人 (年龄≥50岁).
- 针对每个算法,对比了不同组的大脑年龄和时间年龄之间的相关性.
- 检查了预测错误 (大脑年龄与时间年龄) 并进行了灵敏度分析.
主要成果:
- 与白人和西班牙裔美国人相比,非洲裔美国人参与者的大脑年龄和时间年龄之间的相关性始终较弱.
- 在种族/种族群体中观察到中位预测错误的显著差异,根据算法而异.
- 敏感性分析证实了各组之间持续存在的绩效差异.
结论:
- 大脑年龄算法在种族和种族群体之间表现有系统的绩效差异.
- 非洲裔美国人和/或西班牙裔美国人的准确性较低.
- 迫切需要包容性算法开发和验证,以确保公平的神经成像生物标记物应用.
更多相关视频
09:38Generalized Psychophysiological Interaction PPI Analysis of Memory Related Connectivity in Individuals at Genetic Risk for Alzheimer's Disease
Published on: November 14, 2017
15.6K
04:37Author Spotlight: Increasing TMS Accessibility Through Braiding Techniques for Diverse Hair Types
Published on: August 9, 2024
1.3K
相关概念视频
02:55Stereotypes, Prejudice, and Discrimination
94.9K
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...
94.9K
01:29Bias in Epidemiological Studies
1.3K
Biases can arise at various stages of research, from study design and data collection to analysis and interpretation. Recognizing and addressing these biases is essential to ensure the validity and reliability of epidemiological findings.Broadly speaking, biases in epidemiology fall into three main categories: selection bias, information bias, and confounding. A more detailed description of possible biases is:
1.3K