Explainable and programmable hypergraph convolutional network for imaging genetics data fusion

Integrating multi-view information to gain a new understanding of complex disease like Alzheimer’s disease (AD) has great clinical value. Hypergraphs have unique advantages in modeling high-order associations, but current deep learning methods cannot fully utilize the structural information in hypergraphs and have limited application value due to the black-box nature. This paper improves the hypergraph learning in interpretability and programmability. Firstly, we fuse multi-view information by constructing brain region-gene hypergraphs. Secondly, a characteristic information aggregation model is constructed based on hypergraph structure, Finally, a characteristic information aggregation hypergraph convolutional network (CIA-HGCN) is proposed based on the idea of graph neural networks. Evaluated by clinical imaging genetics data, CIA-HGCN obtained accuracy of 88.3% in AD identification task and showed superior performance in characteristic extraction. This paper provides a practical and flexible deep learning method for AD research and clinical applications.