Abstract by Tanner Christensen
Learning Vector-Space Disease Representations from Individual Diagnosis Networks
One of the primary challenges of healthcare delivery is aggregating disparate, asynchronous data sources into meaningful indicators of individual health. We combine natural language word embedding and network modeling techniques to learn meaningful representation of medical concepts by using the weighted network adjacency matrix in the GloVe algorithm. We demonstrate that using our learned embeddings with basic machine learning techniques performs competitively with state-of-the-art models for disease prediction.