EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Characterizing Psychiatric Disorders Through Graph Neural Networks: A Functional Connectivity Analysis of Depression and Schizophrenia

Ji-Won Lee, Ye-Eun Kim, Mikhail Votinov, Minghao Xu, Sun-Young Kim, Munseob Lee, Lisa Wagels, Ute Habel, Han-Gue Jo iD

Depression and Anxiety · 2025

DOI: 10.1155/da/9062022 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Depression and Anxiety, 2025. Verfasst von Ji-Won Lee und 8 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic and Information Engineering, Kunsan National University, Gunsan, Republic of Korea. Hauptthemen laut MEDLINE: Schizophrenia, Major Depressive Disorder, Nerve Net, Brain. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Deutsche Forschungsgemeinschaft, Forschungszentrum Jülich, National Research Council of Science and Technology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

SchizophreniaMajor Depressive DisorderNerve NetBrainNeural Networks, ComputerConnectomeHumansMagnetic Resonance ImagingMaleAdultFemaleMiddle AgedYoung AdultDeep LearningGraph Neural Networks

Autor:innen und Institutionen

  • 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.
  • Institute of Neuroscience and Medicine (INM 10: Brain Structure Function Relationships), Research Centre Jülich, Jülich, Germany.
  • School of Mechanical Engineering, Kunsan National University, Gunsan, Republic of Korea.
  • AI Convergence Research Section, Electronics and Telecommunications Research Institute, Gwangju, Republic of Korea.
  • Department of AI Convergence, College of Computer and Software, Kunsan National University, Gunsan, Republic of Korea.

ORCID-Profile: Han-Gue Jo

Förderung

  • Deutsche Forschungsgemeinschaft
  • Forschungszentrum Jülich
  • National Research Council of Science and Technology
  • RWTH Aachen University

Zitieren

APA

Lee, J. W., Kim, Y. E., Votinov, M., Xu, M., Kim, S. Y., Lee, M., Wagels, L., Habel, U., & Jo, H. G. (2025). Characterizing Psychiatric Disorders Through Graph Neural Networks: A Functional Connectivity Analysis of Depression and Schizophrenia. Depression and Anxiety. https://doi.org/10.1155/da/9062022

Vancouver

Lee JW, Kim YE, Votinov M, Xu M, Kim SY, Lee M, et al. Characterizing Psychiatric Disorders Through Graph Neural Networks: A Functional Connectivity Analysis of Depression and Schizophrenia. Depression and Anxiety. 2025. doi:10.1155/da/9062022

BibTeX
@article{Lee2025,
  author = {Lee, Ji-Won and Kim, Ye-Eun and Votinov, Mikhail and Xu, Minghao and Kim, Sun-Young and Lee, Munseob and Wagels, Lisa and Habel, Ute and Jo, Han-Gue},
  title = {Characterizing Psychiatric Disorders Through Graph Neural Networks: A Functional Connectivity Analysis of Depression and Schizophrenia},
  journal = {Depression and Anxiety},
  year = {2025},
  doi = {10.1155/da/9062022}
}
Kostenlos starten →