Graph neural network (GNN) is another major development after convolutional neural network, and it belongs to an emerging deep learning method in the field of artificial intelligence. It mainly preserves the topological information in graph data through end-to-end learning from graph to prediction, and overcomes the defect that traditional deep learning cannot be applied to non-Euclidean data. This paper demonstrates the advantages of GNN for processing complex non-Euclidean data through the application progress of GNN in brain-related mental and nervous system diseases. GNN shows great potential in the medical field, furthermore, the network structure of the syndrome differentiation system of Traditional Chinese Medicine (TCM) is similar to the structure of the brain active area, and it is highly compatible with the schematic unstructured data processed by GNN, so GNN has great application prospect in the field of TCM. This article summarizes the application of GNN in the field of TCM and brain-related mental and nervous system diseases, and analyzes the advantages of TCM diagnosis and treatment models from the theoretical level, in order to explore and build a GNN-based model for fitting with the thinking mode of "syndrome differentiation and treatment" and realizing the objective diagnosis in TCM. It provides new means for solving the problems of complex relationship representation in TCM and mining the individual characteristics of patients. And it also provides a favorable tool for revealing the potential mechanism of TCM from multiple perspectives, and developing and improving the science of TCM.

graph neural network  /  graph convolutional network  /  Traditional Chinese Medicine  /  brain disease prediction