Using connectome-based predictive modeling to predict individual behavior from brain connectivity.

Using connectome-based predictive modeling to predict individual behavior from brain connectivity.
复制标题

DOI:
10.1038/nprot.2016.178
复制
发表时间:
2017-03
期刊:
影响因子:
14.8
通讯作者:
Constable RT
Constable RT
中科院分区:
生物学1区
文献类型:
--
作者:
Shen X;Finn ES;Scheinost D;Rosenberg MD;Chun MM;Papademetris X;Constable RT

文献摘要

参考文献

被引文献

相似文献

神经成像是一个快速发展的研究领域,它使用功能磁共振成像(FMRI)、扩散张量成像(DTI)和脑电(EEG)等技术收集人脑的解剖和功能图像。技术进步和大规模数据集使模型的发展成为可能,这些模型能够使用从神经成像数据得出的大脑连通性测量来预测个体特征和行为的差异。在这里,我们提出了基于连接组的预测建模(CPM),这是一种数据驱动的协议,用于使用交叉验证从连接性数据开发大脑行为关系的预测模型。该协议包括以下步骤:1)特征选择,2)特征总结,3)模型建立,4)预测意义评估。我们还包括可视化最具预测性的功能(即大脑连接)的建议。最终结果应该是一个可推广的模型,该模型将大脑连通性数据作为输入,并生成对新受试者行为测量的预测,这解释了这些测量中的很大一部分差异。已经证明,在大脑行为预测方面,CPM协议的性能与大多数现有方法相当或更好。然而,由于CPM专注于线性建模和纯粹的数据驱动方法,在机器学习或优化方面经验有限或没有经验的神经科学家会发现很容易实现这些协议。根据要处理的数据量的不同,该协议可能需要10-100分钟进行建模,1-48小时进行置换测试,10-20分钟可视化结果。
Neuroimaging is a fast developing research area where anatomical and functional images of human brains are collected using techniques such as functional magnetic resonance imaging (fMRI), diffusion tensor imaging (DTI), and electroencephalography (EEG). Technical advances and large-scale datasets have allowed for the development of models capable of predicting individual differences in traits and behavior using brain connectivity measures derived from neuroimaging data. Here, we present connectome-based predictive modeling (CPM), a data-driven protocol for developing predictive models of brain-behavior relationships from connectivity data using cross-validation. This protocol includes the following steps: 1) feature selection, 2) feature summarization, 3) model building, and 4) assessment of prediction significance. We also include suggestions for visualizing the most predictive features (i.e., brain connections). The final result should be a generalizable model that takes brain connectivity data as input and generates predictions of behavioral measures in novel subjects, accounting for a significant amount of the variance in these measures. It has been demonstrated that the CPM protocol performs equivalently or better than most of the existing approaches in brain-behavior prediction. However, because CPM focuses on linear modeling and a purely data-driven driven approach, neuroscientists with limited or no experience in machine learning or optimization would find it easy to implement the protocols. Depending on the volume of data to be processed, the protocol can take 10–100 minutes for model building, 1–48 hours for permutation testing, and 10–20 minutes for visualization of results.
静止状态fMRI中的最新进展和运动校正问题。
DOI: 10.1016/j.neuroimage.2014.10.044
发表时间: 2015-01-15
期刊: NeuroImage
影响因子: 5.7
作者:
Power JD;Schlaggar BL;Petersen SE
通讯作者: Petersen SE
DOI: 10.1016/j.clinph.2015.02.060
发表时间: 2015-11-01
影响因子: 4.7
作者:
Khazaee, Ali;Ebrahimzadeh, Ata;Babajani-Feremi, Abbas
通讯作者: Babajani-Feremi, Abbas
DOI: 10.1080/03610927708827533
发表时间: 1977-01-01
期刊: COMMUNICATIONS IN STATISTICS PART A-THEORY AND METHODS
影响因子: --
作者:
HOLLAND, PW;WELSCH, RE
通讯作者: WELSCH, RE
DOI: 10.1038/nn.4179
发表时间: 2016-01
影响因子: 25
作者:
Rosenberg MD;Finn ES;Scheinost D;Papademetris X;Shen X;Constable RT;Chun MM
通讯作者: Chun MM
DOI: 10.3389/fnsys.2012.00062
发表时间: 2012
影响因子: 3
作者:
HD-200 Consortium
通讯作者: HD-200 Consortium