文献检索，用中文搜 PubMed

Vascular cognitive impairment (VCI) is a common complication in adult patients with moyamoya disease (MMD), and is reversible by surgical revascularization in its early stage of mild VCI. However, accurate diagnosis of mild VCI is difficult based on neuropsychological examination alone. This study proposed a method of dynamic resting-state functional connectivity (FC) network to recognize global cognitive impairment in MMD. For MMD, 36 patients with VCI and 43 patients with intact cognition (Non-VCI) were included, as well as 26 normal controls (NCs). Using resting-state fMRI, dynamic low-order FC networks were first constructed with multiple brain regions which were generated through a sliding window approach and correlated in temporal dimension. In order to obtain more information of network interactions along the time, high-order FC networks were established by calculating correlations among each pair of brain regions. Afterwards, a sparse representation-based classifier was constructed to recognize MMD (experiment 1) and its cognitive impairment (experiment 2) with features extracted from both low- and high-order FC networks. Finally, the ten-fold cross-validation strategy was proposed to train and validate the performance of the classifier. The three groups did not differ significantly in demographic features ( > 0.05), while the VCI group exhibited the lowest MMSE scores ( = 0.001). The Non-VCI and NCs groups did not differ significantly in MMSE scores ( = 0.054). As for the classification between MMD and NCs, the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity of the classifier reached 90.70, 88.57, 93.67, and 73.08%, respectively. While for the classification between VCI and Non-VCI, the AUC, accuracy, sensitivity, and specificity of the classifier reached 91.02, 84.81, 80.56, and 88.37%, respectively. This study not only develops a promising classifier to recognize VCI in adult MMD in its early stage, but also implies the significance of time-varying properties in dynamic FC networks.

血管性认知障碍（VCI）是成人烟雾病（MMD）患者的常见并发症，在轻度 VCI 的早期阶段通过手术血运重建是可逆的。然而，仅通过神经心理学检查来准确诊断轻度 VCI 是困难的。本研究提出了一种动态静息状态功能连接（FC）网络方法来识别 MMD 中的整体认知障碍。

对于 MMD，纳入了 36 例 VCI 患者和 43 例认知完整（非 VCI）患者，以及 26 例正常对照（NCs）。使用静息态 fMRI，首先通过滑动窗口方法生成多个脑区，构建动态低阶 FC 网络，并在时间维度上进行相关性分析。为了获得沿时间的网络相互作用的更多信息，通过计算每个脑区之间的相关性来构建高阶 FC 网络。然后，构建基于稀疏表示的分类器，使用从低阶和高阶 FC 网络中提取的特征来识别 MMD（实验 1）及其认知障碍（实验 2）。最后，提出了十折交叉验证策略来训练和验证分类器的性能。三组在人口统计学特征上无显著差异（>0.05），而 VCI 组的 MMSE 评分最低（=0.001）。非 VCI 和 NCs 组的 MMSE 评分无显著差异（=0.054）。对于 MMD 和 NCs 之间的分类，分类器的受试者工作特征曲线（ROC）下面积（AUC）、准确性、敏感性和特异性分别达到 90.70%、88.57%、93.67%和 73.08%。对于 VCI 和非 VCI 之间的分类，分类器的 AUC、准确性、敏感性和特异性分别达到 91.02%、84.81%、80.56%和 88.37%。

本研究不仅开发了一种有前途的分类器来识别成人 MMD 早期的 VCI，还暗示了动态 FC 网络中时变特性的重要性。