Zhou Lijun, Zhu Hongru, Liu Yunfei, Mo Xian, Yuan Jun, Luo Changyu, Zhang Junran
College of Electrical Engineering, Sichuan University, Chengdu 610065, P. R. China.
College of Electrical Engineering, Northwest Minzu University, Lanzhou 730030, P. R. China.
Sheng Wu Yi Xue Gong Cheng Xue Za Zhi. 2024 Dec 25;41(6):1110-1118. doi: 10.7507/1001-5515.202407031.
Post-traumatic stress disorder (PTSD) presents with complex and diverse clinical manifestations, making accurate and objective diagnosis challenging when relying solely on clinical assessments. Therefore, there is an urgent need to develop reliable and objective auxiliary diagnostic models to provide effective diagnosis for PTSD patients. Currently, the application of graph neural networks for representing PTSD is limited by the expressiveness of existing models, which does not yield optimal classification results. To address this, we proposed a multi-graph multi-kernel graph convolutional network (MK-GCN) model for classifying PTSD data. First, we constructed functional connectivity matrices at different scales for the same subjects using different atlases, followed by employing the k-nearest neighbors algorithm to build the graphs. Second, we introduced the MK-GCN methodology to enhance the feature extraction capability of brain structures at different scales for the same subjects. Finally, we classified the extracted features from multiple scales and utilized graph class activation mapping to identify the top 10 brain regions contributing to classification. Experimental results on seismic-induced PTSD data demonstrated that our model achieved an accuracy of 84.75%, a specificity of 84.02%, and an AUC of 85% in the classification task distinguishing between PTSD patients and non-affected subjects. The findings provide robust evidence for the auxiliary diagnosis of PTSD following earthquakes and hold promise for reliably identifying specific brain regions in other PTSD diagnostic contexts, offering valuable references for clinicians.
创伤后应激障碍（PTSD）临床表现复杂多样，仅依靠临床评估进行准确客观的诊断具有挑战性。因此，迫切需要开发可靠、客观的辅助诊断模型，为PTSD患者提供有效的诊断。目前，图神经网络在PTSD表征方面的应用受到现有模型表达能力的限制，无法产生最优分类结果。为解决这一问题，我们提出了一种用于PTSD数据分类的多图多核图卷积网络（MK-GCN）模型。首先，我们使用不同图谱为同一受试者构建不同尺度的功能连接矩阵，然后采用k近邻算法构建图。其次，我们引入MK-GCN方法来增强同一受试者不同尺度脑结构的特征提取能力。最后，我们对从多个尺度提取的特征进行分类，并利用图类激活映射来识别对分类贡献最大的前10个脑区。地震诱发PTSD数据的实验结果表明，在区分PTSD患者和未受影响受试者的分类任务中，我们的模型准确率达到84.75%，特异性为84.02%，AUC为85%。这些发现为地震后PTSD的辅助诊断提供了有力证据，并有望在其他PTSD诊断环境中可靠地识别特定脑区，为临床医生提供有价值的参考。
