arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.05407cs.AI
收藏

脑网络中因果充分性必要外生节点的算法识别

Algorithmic Identification of Essential Exogenous Nodes for Causal Sufficiency in Brain Networks

School of Electrical and Computer Engineering, University of Tehran(德黑兰大学电气与计算机工程学院);Harvard Medical School(哈佛医学院)

Abdolmahdi Bagheri, Mahdi Dehshiri, Babak Nadjar Araabi, Alireza Akhondi Asl

AI总结:

提出算法识别脑网络中因果充分性所需的外生节点,结合PC算法、KS检验和NF-iVAE,在HCP数据上验证背侧区域为视觉网络混杂因素。

摘要:

在任何因果机制的研究中,例如大脑的因果网络,因果充分性假设起着关键作用。值得注意的是,忽视这一假设可能导致显著错误,这一事实在脑网络的因果分析中常常被忽视。在本研究中,我们提出了一种算法识别方法,用于确定满足因果充分性关键需求所必需的外生节点,以便在此类探究中遵循该假设。我们的方法包括三个主要步骤:首先,通过捕捉Peter-Clark(PC)算法的精髓,我们对网络内区域对进行独立性检验,并针对来自其他网络的节点条件化处理相同区域对。接下来,我们通过分析条件结果与无条件结果之间的差异,使用Kolmogorov-Smirnov检验来区分候选混杂因素。随后,我们利用非因子化可识别变分自编码器(NF-iVAE)以及相关系数指数(CCI)指标来识别这些候选节点中的混杂变量。将我们的方法应用于人类连接组计划(HCP)电影观看任务数据,我们证明尽管背侧和腹侧区域之间存在交互作用,但只有背侧区域作为视觉网络的混杂因素,反之亦然。这些发现与神经科学视角得出的结果一致。最后,我们通过测试NF-iVAE初始化的30次独立运行来展示我们结果的可靠性。

英文摘要:

In the investigation of any causal mechanisms, such as the brain's causal networks, the assumption of causal sufficiency plays a critical role. Notably, neglecting this assumption can result in significant errors, a fact that is often disregarded in the causal analysis of brain networks. In this study, we propose an algorithmic identification approach for determining essential exogenous nodes that satisfy the critical need for causal sufficiency to adhere to it in such inquiries. Our approach consists of three main steps: First, by capturing the essence of the Peter-Clark (PC) algorithm, we conduct independence tests for pairs of regions within a network, as well as for the same pairs conditioned on nodes from other networks. Next, we distinguish candidate confounders by analyzing the differences between the conditional and unconditional results, using the Kolmogorov-Smirnov test. Subsequently, we utilize Non-Factorized identifiable Variational Autoencoders (NF-iVAE) along with the Correlation Coefficient index (CCI) metric to identify the confounding variables within these candidate nodes. Applying our method to the Human Connectome Projects (HCP) movie-watching task data, we demonstrate that while interactions exist between dorsal and ventral regions, only dorsal regions serve as confounders for the visual networks, and vice versa. These findings align consistently with those resulting from the neuroscientific perspective. Finally, we show the reliability of our results by testing 30 independent runs for NF-iVAE initialization.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑