English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

There is a recent trend to leverage the power of graph neural networks (GNNs)for brain-network based psychiatric diagnosis, which,in turn, also motivates anurgent need for psychiatrists to fully understand the decision behavior of theused GNNs. However, most of the existing GNN explainers are either post-hoc inwhich another interpretive model needs to be created to explain a well-trainedGNN, or do not consider the causal relationship between the extractedexplanation and the decision, such that the explanation itself containsspurious correlations and suffers from weak faithfulness. In this work, wepropose a granger causality-inspired graph neural network (CI-GNN), a built-ininterpretable model that is able to identify the most influential subgraph(i.e., functional connectivity within brain regions) that is causally relatedto the decision (e.g., major depressive disorder patients or healthy controls),without the training of an auxillary interpretive network. CI-GNN learnsdisentangled subgraph-level representations {\alpha} and \b{eta} that encode,respectively, the causal and noncausal aspects of original graph under a graphvariational autoencoder framework, regularized by a conditional mutualinformation (CMI) constraint. We theoretically justify the validity of the CMIregulation in capturing the causal relationship. We also empirically evaluatethe performance of CI-GNN against three baseline GNNs and four state-of-the-artGNN explainers on synthetic data and three large-scale brain disease datasets.We observe that CI-GNN achieves the best performance in a wide range of metricsand provides more reliable and concise explanations which have clinicalevidence.

CI-GNN: A Granger Causality-Inspired Graph Neural Network for Interpretable Brain Network-Based Psychiatric Diagnosis