Lee Ji-Won, Kim Ye-Eun, Votinov Mikhail, Xu Minghao, Kim Sun-Young, Lee Munseob, Wagels Lisa, Habel Ute, Jo Han-Gue
School of Electronic and Information Engineering, Kunsan National University, Gunsan, Republic of Korea.
Department of Psychiatry, Psychotherapy and Psychosomatics, Medical Faculty RWTH Aachen University, Aachen, Germany.
Depress Anxiety. 2025 Aug 22;2025:9062022. doi: 10.1155/da/9062022. eCollection 2025.
Major depressive disorder (MDD) and schizophrenia (SZ) are among the most debilitating psychiatric disorders, characterized by widespread disruptions in large-scale brain networks. However, the commonalities and distinctions in their large-scale network distributions remain unclear. The present study aimed to leverage advanced deep learning techniques to identify these common and distinct patterns, providing insights into the shared and disorder-specific neural mechanisms underlying MDD and SZ. Recent advances in graph neural networks (GNNs) offer a powerful framework for analyzing brain connectivity patterns, enabling automated learning of complex, high-dimensional network features. In this study, we applied state-of-art GNN architectures to classify MDD and SZ patients from healthy controls (HCs), respectively, using a multisite resting-state fMRI dataset. The attention-based hierarchical pooling GNN (SAGPool) model achieved the highest performance, with mean accuracies of 71.50% for MDD and 75.65% for SZ classification. Using a perturbation-based explainability method, we identified prominent functional connections driving model decisions, revealing distinct patterns of the large-scale network disruption across disorders. In MDD, alterations were dominantly observed in the default mode network (DMN), whereas SZ exhibited prominent alterations in the ventral attention network (VAN). Notably, specific functional connections identified by our model showed significant correlations with clinical symptoms, particularly positive and general symptoms measured by the positive and negative syndrome scale (PANSS) in SZ patients. Our findings demonstrate the utility of GNNs for uncovering complex connectivity patterns in psychiatric disorders and provide novel insights into the distinct neural mechanisms underlying MDD and SZ. These results highlight the potential of graph-based models as tools for both diagnostic classification and biomarker discovery in psychiatric research.
重度抑郁症（MDD）和精神分裂症（SZ）是最具致残性的精神疾病，其特征是大规模脑网络广泛紊乱。然而，它们在大规模网络分布中的共性和差异仍不清楚。本研究旨在利用先进的深度学习技术来识别这些共同和不同的模式，从而深入了解MDD和SZ潜在的共同和特定于疾病的神经机制。图神经网络（GNN）的最新进展为分析脑连接模式提供了一个强大的框架，能够自动学习复杂的高维网络特征。在本研究中，我们应用最先进的GNN架构，使用多站点静息态功能磁共振成像（fMRI）数据集，分别将MDD和SZ患者与健康对照（HC）进行分类。基于注意力的分层池化GNN（SAGPool）模型取得了最高的性能，MDD分类的平均准确率为71.50%，SZ分类的平均准确率为75.65%。使用基于扰动的可解释性方法，我们确定了驱动模型决策的突出功能连接，揭示了不同疾病中大规模网络破坏的不同模式。在MDD中，主要在默认模式网络（DMN）中观察到改变，而SZ在腹侧注意网络（VAN）中表现出明显的改变。值得注意的是，我们的模型识别出的特定功能连接与临床症状显著相关，特别是SZ患者中由阳性和阴性症状量表（PANSS）测量的阳性和一般症状。我们的研究结果证明了GNN在揭示精神疾病复杂连接模式方面的效用，并为MDD和SZ潜在的不同神经机制提供了新的见解。这些结果突出了基于图的模型作为精神疾病研究中诊断分类和生物标志物发现工具的潜力。
