Covariate Correcting Networks for Identifying Associations Between Socioeconomic Factors and Brain Outcomes in Children

Covariate Correcting Networks for Identifying Associations Between Socioeconomic Factors and Brain Outcomes in Children
复制标题

用于识别社会经济因素与儿童大脑结果之间关联的协变量校正网络

DOI:
10.1007/978-3-030-87234-2_40
复制
发表时间:
2021
期刊:
Medical Image Computing and Computer Assisted Intervention (MICCAI
影响因子:
--
通讯作者:
Kim, Won Hwa
Kim, Won Hwa
中科院分区:
--
文献类型:
--
作者:
Cho, Hyuna;Park, Gunwoong;Isaiah, Amal;Kim, Won Hwa

文献摘要

参考文献

相似文献

青春期脑发育受年龄、教育、社会经济条件等多种因素的综合影响。要从感兴趣的变量中识别独立效应(例如,社会经济条件),通常采用诸如通用线性模型(GLM)的统计模型来解释协变量(例如,年龄和性别)。然而,由于样本量不足和离群值,统计模型可能很脆弱,并且对全脑分析进行多次测试会导致不可避免的假阳性,而没有足够的灵敏度。因此,有必要为多个测试开发一个统一的框架,以稳健地拟合观察结果并提高灵敏度。因此,我们提出了一个统一的灵活的神经网络,优化的主要变量的贡献,在原来的GLM,这导致改进的统计结果。对青少年脑认知发育(ABCD)研究的弥散张量图像的分数各向异性(FA)进行组分析的结果表明,与传统方法相比,所提出的方法提供了更有选择性和更有意义的与社会经济地位相关的ROI检测。
Brain development in adolescence is synthetically influenced by various factors such as age, education, and socioeconomic conditions. To identify an independent effect from a variable of interest (e.g., socioeconomic conditions), statistical models such as General Linear Model (GLM) are typically adopted to account for covariates (e.g., age and gender). However, statistical models may be vulnerable with insufficient sample size and outliers, and multiple tests for a whole brain analysis lead to inevitable false-positives without sufficient sensitivity. Hence, it is necessary to develop a unified framework for multiple tests that robustly fits the observation and increases sensitivity. We therefore propose a unified flexible neural network that optimizes on the contribution from the main variable of interest as introduced in original GLM, which leads to improved statistical outcomes. The results on group analysis with fractional anisotropy (FA) from Diffusion Tensor Images from Adolescent Brain Cognitive Development (ABCD) study demonstrate that the proposed method provides much more selective and meaningful detection of ROIs related to socioeconomic status over conventional methods.
通过改进的排序方法提高异常值分布的方差分析 F 检验的功效
DOI: --
发表时间: 1995
期刊:
影响因子: --
作者:
D. W. Zimmerman
通讯作者: D. W. Zimmerman
DOI: 10.1038/s41591-019-0713-y
发表时间: 2020-01-01
期刊: NATURE MEDICINE
影响因子: 82.9
作者:
Marshall, Andrew T.;Betts, Samantha;Sowell, Elizabeth R.
通讯作者: Sowell, Elizabeth R.
DOI: 10.1016/s0006-8993(01)03232-2
发表时间: 2002-01-11
期刊: BRAIN RESEARCH
影响因子: 2.9
作者:
Lambert, S;Sampaio, E;Mauss, Y
通讯作者: Mauss, Y
DOI: 10.3390/microorganisms7010017
发表时间: 2019-01-01
期刊: MICROORGANISMS
影响因子: 4.5
作者:
Bowyer, Ruth C. E.;Jackson, Matthew A.;Steves, Claire J.
通讯作者: Steves, Claire J.
DOI: 10.1079/bjn2001485
发表时间: 2002-01-01
影响因子: 3.6
作者:
Ivanovic, DM;Leiva, BP;Bosch, EO
通讯作者: Bosch, EO