Identifying the presence of Parkinson's disease using low-frequency fluctuations in BOLD signals
Identifying the presence of Parkinson's disease using low-frequency fluctuations in BOLD signals
复制标题
使用 BOLD 信号的低频波动识别帕金森病的存在
DOI：
10.1016/j.neulet.2017.02.056
复制
发表时间：
2017
影响因子：
2.5
通讯作者：
Guo Ji feng
中科院分区：
文献类型：
--
作者：
Tang Yan;Meng Li;Wan Chang min;Liu Zhen hua;Liao Wei hua;Yan Xin xiang;Wang Xiao yu;Tang Bei sha;Guo Ji feng
帕金森病是一种慢性进行性退行性神经系统疾病，以黑质多巴胺神经元变性和细胞内路易氏包涵体形成为特征。静息功能磁共振成像(RS-fMRI)已证实帕金森病患者代谢模式改变的证据。这项研究的目的是确定是否可以根据血氧水平依赖信号的静息波动来“预测”帕金森病的存在。我们用RS-fMRI测量了51例PD患者和50例年龄、性别匹配的健康对照的低频波动幅度(Alff)和分数Alff(FALFF)。与健康对照组相比，帕金森病患者双侧舌回和左侧壳核的ALFF改变，右侧小脑后叶的FALFF值改变。支持向量机(SVMs)包括一种能够在个体水平进行预测的监督模式识别方法，它被训练成基于Alff和fALFF将PD患者与健康对照区分开来。使用留一交叉验证法分析样本，我们可靠地区分帕金森病患者和对照组，敏感度和特异度分别为92%和87%。总体而言，这些发现表明，支持向量机-神经成像方法可能具有特殊的临床价值，因为它能够在个体水平上准确地识别帕金森病。应考虑将RS-fMRI作为评估PD的生物标记物和分析工具。
Parkinson’s disease (PD) is a chronic, progressive, and degenerative neurological disorder that is characterized by the degeneration of dopamine neurons in the substantia nigra and the formation of intracellular Lewy inclusion bodies. Resting-state functional magnetic resonance imaging (RS-fMRI) has demonstrated evidence of changes in metabolic patterns in individuals with PD. The purpose of this study was to determine whether the presence of PD could be “predicted” based on resting fluctuations in the blood oxygenation level dependent signal. We utilized RS-fMRI to measure the amplitude of low-frequency fluctuation (ALFF) and the fractional ALFF (fALFF) in 51 patients with PD and 50 age- and sex-matched healthy controls. Compared with the healthy controls, the individuals with PD exhibited altered ALFFs in the bilateral lingual gyrus and left putamen and an altered fALFF in the right cerebellum posterior lobe. Support vector machines (SVMs), which comprise a supervised pattern recognition method that enables predictions at the individual level, were trained to separate individuals with PD from healthy controls based on the ALFF and fALFF. Using the leave-one-out cross-validation method to analyze our sample, we reliably distinguished the participants with PD from the controls with 92% sensitivity and 87% specificity. Overall, these findings suggest that the SVM-neuroimaging approach may be of particular clinical value because it enables the accurate identification of PD at the individual level. RS-fMRI should be considered for development as a biomarker and an analytical tool for the evaluation of PD.