Application of clustering analyses to the diagnosis of Huntington disease in mice and other diseases with well-defined group boundaries.

Application of clustering analyses to the diagnosis of Huntington disease in mice and other diseases with well-defined group boundaries.
复制标题

聚集分析在小鼠和其他定义群界的其他疾病中的诊断中的应用。

DOI:
10.1016/j.cmpb.2011.03.004
复制
发表时间:
2011-12
影响因子:
6.1
通讯作者:
Low WC
Low WC
中科院分区:
工程技术2区
文献类型:
--
作者:
Nikas JB;Low WC

文献摘要

参考文献

被引文献

相似文献

核磁共振(NMR)光谱学已经成为一种可以提供体内器官系统内代谢物信息的技术。在这项研究中,我们介绍了一种新的方法,采用聚类算法来开发一个诊断模型,可以区分诊断一个单一的未知主题的疾病与明确的组边界。我们使用了三个测试来评估的适用性和准确性所需的诊断目的的四个聚类算法,我们调查(K-均值,模糊,分层,和Medoid分区)。为了实现这一目标,我们使用高场体内质子NMR光谱(9.4特斯拉)研究了R6/2亨廷顿病(HD)转基因小鼠和野生型(WT)小鼠的纹状体代谢谱。我们测试了所有四种聚类算法:1)使用原始R6/2 HD小鼠和WT小鼠,2)使用未知小鼠,其状态已通过基因分型确定,以及3)将原始R6/2小鼠分为两个年龄亚组(8周龄和12周龄)的能力。只有我们的诊断模型采用ROC监督模糊,无监督模糊和ROC监督K均值聚类通过了所有三个严格的测试,准确率为100%,这表明它们可以用于诊断目的。
Nuclear magnetic resonance (NMR) spectroscopy has emerged as a technology that can provide metabolite information within organ systems in vivo. In this study, we introduced a new method of employing a clustering algorithm to develop a diagnostic model that can differentially diagnose a single unknown subject in a disease with well-defined group boundaries. We used three tests to assess the suitability and the accuracy required for diagnostic purposes of the four clustering algorithms we investigated (K-means, Fuzzy, Hierarchical, and Medoid Partitioning). To accomplish this goal, we studied the striatal metabolomic profile of R6/2 Huntington disease (HD) transgenic mice and that of wild type (WT) mice using high field in vivo proton NMR spectroscopy (9.4 Tesla). We tested all four clustering algorithms 1) with the original R6/2 HD mice and WT mice, 2) with unknown mice, whose status had been determined via genotyping, and 3) with the ability to separate the original R6/2 mice into the two age subgroups (8 and 12 wks old). Only our diagnostic models that employed ROC-supervised Fuzzy, unsupervised Fuzzy, and ROC-supervised K-means clustering passed all three stringent tests with 100% accuracy, indicating that they may be used for diagnostic purposes.
DOI: 10.1038/nature03702
发表时间: 2005-06-09
期刊: NATURE
影响因子: 64.8
作者:
Lu, J;Getz, G;Golub, TR
通讯作者: Golub, TR
DOI: 10.1002/mrm.20184
发表时间: 2004-09-01
影响因子: 3.3
作者:
Tk치c, I;Henry, PG;Gruetter, R
通讯作者: Gruetter, R
DOI: 10.1016/j.bbrc.2005.06.128
发表时间: 2005-08-26
影响因子: 3.1
作者:
Shen, HB;Yang, J;Chou, KC
通讯作者: Chou, KC
在诊断和评估疾病的临床变化中,比较了鉴定关键的核磁共振光谱生物标志物的分析数学方法的比较。
DOI: 10.1002/cne.22365
发表时间: 2010-10-15
期刊: The Journal of comparative neurology
影响因子: --
作者:
Nikas JB;Keene CD;Low WC
通讯作者: Low WC
DOI: 10.1073/pnas.0711983105
发表时间: 2008-02-26
影响因子: 11.1
作者:
Lowry, W. E.;Richter, L.;Plath, K.
通讯作者: Plath, K.