Latent-Graph Learning for Disease Prediction. (arXiv:2003.13620v2 [cs.LG] UPDATED)

Recently, Graph Convolutional Networks (GCNs) have proven to be a powerful
machine learning tool for Computer-Aided Diagnosis (CADx) and disease
prediction. A key component in these models is to build a population graph,
where the graph adjacency matrix represents pair-wise patient similarities.
Until now, the similarity metrics have been defined manually, usually based on
meta-features like demographics or clinical scores. The definition of the
metric, however, needs careful tuning, as GCNs are very sensitive to the graph
structure. In this …

arxiv disease graph graph learning learning prediction