This paper presents a new method for disease prediction using graph convolutional networks. Specifically, it focuses on the prediction of neurodevelopmental and neurodegenerative brain disorders, such as autism spectrum disorder and Alzheimer’s disease. The model proposed in the study incorporates both imaging and non-imaging features into graph nodes and edges, providing a holistic perspective on brain disorders. The method was tested on two large datasets and showed competitive performance and significant improvements in classification accuracy.
Publication date: 14 Nov 2023
Project Page: Not provided
Paper: https://arxiv.org/pdf/2311.07370
