Complex biomarker discovery in neuroimaging data: Finding a needle in a haystack.
Complex biomarker discovery in neuroimaging data: Finding a needle in a haystack.
复制标题
DOI：
10.1016/j.nicl.2013.07.004
复制
发表时间：
2013-08-07
影响因子：
4.2
通讯作者：
Kumar, Vipin
中科院分区：
文献类型：
--
作者：
Atluri, Gowtham;Padmanabhan, Kanchana;Fang, Gang;Steinbach, Michael;Petrella, Jeffrey R.;Lim, Kelvin;MacDonald, Angus, III;Samatova, Nagiza F.;Doraiswamy, P. Murali;Kumar, Vipin
精神分裂症、双相情感障碍和阿尔茨海默病等神经精神障碍是主要的公共卫生问题。然而，尽管经过了几十年的研究，我们目前还没有经过验证的预后或诊断测试，可以应用于单个患者的水平。许多神经精神疾病是由于人脑中发生的一系列变化，而不是局部损害的结果。虽然人们希望新的成像技术，如功能和解剖连接MRI或分子成像可能会提供突破，但使用这些数据集发现的单一生物标记物由于无法捕捉大多数多因素大脑疾病的异质性和复杂性而受到限制。最近，人们利用神经成像数据探索了复杂的生物标记物来解决这一限制。在这篇手稿中，我们考虑了最近文献中正在研究的复杂生物标记物的性质，并提供了在数据挖掘、统计学、机器学习和生物信息学的相关领域中开发的寻找此类生物标记物的技术。我们回顾了发现四种复杂生物标志物的数据挖掘方法。线性生物标记物捕捉与表型相关的线性组合。在一项研究中，组合生物标记物捕捉到了异质样本的生物标记物。通路生物标记物研究已知子系统在特定疾病中的作用。网络生物标记物捕捉到了大脑网络结构在表型中的作用。
Neuropsychiatric disorders such as schizophrenia, bipolar disorder and Alzheimer's disease are major public health problems. However, despite decades of research, we currently have no validated prognostic or diagnostic tests that can be applied at an individual patient level. Many neuropsychiatric diseases are due to a combination of alterations that occur in a human brain rather than the result of localized lesions. While there is hope that newer imaging technologies such as functional and anatomic connectivity MRI or molecular imaging may offer breakthroughs, the single biomarkers that are discovered using these datasets are limited by their inability to capture the heterogeneity and complexity of most multifactorial brain disorders. Recently, complex biomarkers have been explored to address this limitation using neuroimaging data. In this manuscript we consider the nature of complex biomarkers being investigated in the recent literature and present techniques to find such biomarkers that have been developed in related areas of data mining, statistics, machine learning and bioinformatics. We review data mining approaches for discovering four types of complex biomarkers. Linear biomarkers capture linear combinations that are related to the phenotype. Combinatorial biomarkers capture biomarkers for heterogeneous samples in a study. Pathway biomarkers study the role of known subsystems for a given disorder. Network biomarkers capture the role of brain network structure in a phenotype.
登录
查看更多内容
DOI：
10.1523/jneurosci.1929-08.2008
发表时间：
2008-09-10
期刊：
The Journal of neuroscience : the official journal of the Society for Neuroscience
影响因子：
--
作者：
Bassett DS;Bullmore E;Verchinski BA;Mattay VS;Weinberger DR;Meyer-Lindenberg A
通讯作者：
Meyer-Lindenberg A
影响因子：
5.7
作者：
Bassett, Danielle S.;Nelson, Brent G.;Mueller, Bryon A.;Camchong, Jazmin;Lim, Kelvin O.
通讯作者：
Lim, Kelvin O.
影响因子：
5.7
作者：
Alexander-Bloch, Aaron;Lambiotte, Renaud;Roberts, Ben;Giedd, Jay;Gogtay, Nitin;Bullmore, Edward T.
通讯作者：
Bullmore, Edward T.
影响因子：
5.7
作者：
Bunea F;She Y;Ombao H;Gongvatana A;Devlin K;Cohen R
通讯作者：
Cohen R
影响因子：
--
作者：
Chen Z;Padmanabhan K;Rocha AM;Shpanskaya Y;Mihelcic JR;Scott K;Samatova NF
通讯作者：
Samatova NF