Table 1_Abnormal subthalamic nucleus functional connectivity and machine learning classification in Parkinson’s disease: a multisite functional magnetic resonance imaging study.docx

IntroductionParkinson’s disease (PD) is a progressive neurodegenerative disorder imposing a significant global burden, characterized by motor dysfunction linked to aberrant basal ganglia activity. This multisite study analyzed pooled resting-state functional magnetic resonance imaging (rs-fMRI) data to characterize subthalamic nucleus (STN) functional connectivity (FC) abnormalities and to evaluate their utility in machine learning classification of PD.
MethodsWe analyzed rs-fMRI data from 232 participants (158 PD patients and 74 healthy controls [HCs]) across four repositories: Parkinson’s Progression Markers Initiative (PPMI), OpenfMRI, and FCP/INDI (NEUROCON dataset and Tao Wu dataset). Seed-based FC analysis focused on bilateral STNs. Group comparisons (PD vs. HCs) were assessed using two-sample t-tests with Gaussian Random Field (GRF) correction. A support vector machine (SVM) classifier, incorporating significant FC features, was used for diagnostic classification.
ResultsPatients with PD exhibited significant bilateral reductions in STN FC compared to HCs. Specifically, the left STN showed decreased connectivity with the left superior temporal gyrus and the right supramarginal gyrus, whereas the right STN showed decreased connectivity with the right superior temporal gyrus, the left middle temporal gyrus, and the left inferior frontal gyrus (voxel p < 0.005, cluster p < 0.05, GRF corrected). The SVM classifier based on these FC features achieved high diagnostic accuracy (89.1%), sensitivity (97.7%), specificity (75.8%), and an area under the receiver operating characteristic (ROC) curve (AUC) of 0.931 in the validation set.
ConclusionThis study suggests that STN-temporal/parietal hypoconnectivity warrants further investigation as a possible core feature of PD. Furthermore, it demonstrates the high translational potential of STN-centric FC patterns as diagnostic biomarkers when integrated with machine learning, paving the way for improved PD classification and future applications in personalized neuromodulation strategies.

引言
帕金森病（Parkinson’s disease, PD）是一种进行性神经退行性疾病，在全球范围内造成沉重疾病负担，其特征为与基底节活动异常相关的运动功能障碍。本多中心研究整合了静息态功能磁共振成像（resting-state functional magnetic resonance imaging, rs-fMRI）数据，旨在刻画丘脑底核（subthalamic nucleus, STN）的功能连接（functional connectivity, FC）异常特征，并评估其在帕金森病机器学习分类中的应用价值。
方法
本研究分析了来自4个数据库的232名受试者的rs-fMRI数据，其中包括158名帕金森病患者与74名健康对照（healthy controls, HCs），数据库涵盖帕金森病进展标记物倡议（Parkinson’s Progression Markers Initiative, PPMI）、OpenfMRI以及FCP/INDI（包含NEUROCON数据集与Tao Wu数据集）。基于种子点的功能连接分析以双侧丘脑底核为种子区域。组间比较（帕金森病患者vs健康对照）采用两样本t检验结合高斯随机场（Gaussian Random Field, GRF）校正。本研究采用纳入显著功能连接特征的支持向量机（support vector machine, SVM）分类器进行诊断分类。
结果
与健康对照相比，帕金森病患者的双侧丘脑底核功能连接均显著降低。具体而言，左侧丘脑底核与左侧颞上回、右侧缘上回的功能连接显著降低；右侧丘脑底核则与右侧颞上回、左侧颞中回及左侧额下回的功能连接显著降低（体素p<0.005，簇水平p<0.05，经高斯随机场校正）。基于上述功能连接特征的支持向量机分类器在验证集上实现了较高的诊断准确率（89.1%）、灵敏度（97.7%）、特异度（75.8%），且受试者工作特征（receiver operating characteristic, ROC）曲线下面积（AUC）达0.931。
结论
本研究表明，丘脑底核-颞叶/顶叶连接减弱作为帕金森病潜在核心特征，值得进一步深入研究。此外，本研究证实，以丘脑底核为中心的功能连接模式结合机器学习后，具备作为诊断生物标志物的高转化潜力，为优化帕金森病分类及未来个性化神经调控策略的应用奠定了基础。