Optimizing graph neural network architectures for schizophrenia spectrum disorder prediction using evolutionary algorithms

Shurun Wang, Hao Tang, Ryutaro Himeno, Jordi Solé-Casals, Cesar F. Caiafa, Shuning Han, Shigeki Aoki, Zhe Sun

Abstract: Highlights•We propose a GNAS framework to build GNN model for disorder prediction.•We compare our model with other popular ML and DL models on multi-site datasets.•We use the GNNExplainer method to provide the explainability of the model.•The explainability results provide valuable insights for diagnosis and treatment.•The source code is available on GitHub at https://github.com/Shurun-Wang/EA-GNAS.