The cognitive impairment in schizophrenia (SZ) is characterized by significant deficits in working memory task. In order to explore the brain changes of SZ during a working memory task, we performed time-domain and time–frequency analysis of event related potentials (ERP) of SZ during a 0-back task. The P3 wave amplitude was found to be significantly lower in SZ patients than in healthy controls (HC) (p < 0.05). The power in the θ and α bands was significantly enhanced in the SZ group 200 ms after stimulation, while the θ band was significantly enhanced and the β band was weakened in the HC group. Furthermore, phase lag index (PLI) based brain functional connectivity maps showed differences in the connections between parietal and frontotemporal lobes between SZ and HC (p < 0.05). Due to the natural similarity between brain networks and graph data, and the fact that graph attention network can aggregate the features of adjacent nodes, it has more advantages in learning the features of brain regions. We propose a multi graph attention network model combined with adaptive initial residual (AIR) for SZ classification, which achieves an accuracy of 90.90 % and 78.57 % on an open dataset (Zenodo) and our 0-back dataset, respectively. Overall, the proposed methodology offers promising potential for understanding the brain functional connections of schizophrenia.

中文翻译：

---

基于多图注意网络的精神分裂症工作记忆脑网络分析

精神分裂症（SZ）认知障碍的特点是工作记忆任务显着缺陷。为了探索工作记忆任务期间 SZ 的大脑变化，我们对 0-back 任务期间 SZ 的事件相关电位（ERP）进行了时域和时频分析。发现 SZ 患者的 P3 波振幅显着低于健康对照 (HC) (p < 0.05)。刺激后200 ms，SZ组θ和α带的功率显着增强，而HC组θ带显着增强，β带减弱。此外，基于相位滞后指数 (PLI) 的大脑功能连接图显示 SZ 和 HC 之间顶叶和额颞叶之间的连接存在差异 (p < 0.05)。由于脑网络与图数据之间的天然相似性，并且图注意力网络可以聚合相邻节点的特征，因此在学习脑区域特征方面更具优势。我们提出了一种与自适应初始残差（AIR）相结合的多图注意力网络模型，用于 SZ 分类，在开放数据集（Zenodo）和我们的 0-back 数据集上分别实现了 90.90% 和 78.57% 的准确率。总体而言，所提出的方法为理解精神分裂症的大脑功能连接提供了有希望的潜力。