Multi-layer Representation Learning for Medical Concepts
Edward Choi*, Georgia Institute of Technolog; Mohammad Bahadori, Georgia Institute of Technology; Jimeng Sun, Georgia Institute of Technology
Proper representations of medical concepts such as diagnosis, medication, procedure codes and visits from Electronic Health Records (EHR) has broad applications in healthcare analytics. Patient EHR data consists of a sequence of visits over time, where each visit includes multiple medical concepts, e.g., diagnosis, procedure, and medication codes. This hierarchical structure provides two types of relational information, namely sequential order of visits and co-occurrence of the codes within a visit. In this work, we propose Med2Vec, which not only learns the representations for both medical codes and visits from large EHR datasets with over million visits, but also allows us to interpret the learned representations conﬁrmed positively by clinical experts. In the experiments, Med2Vec shows signiﬁcant improvement in prediction accuracy in clinical applications compared to baselines such as Skip-gram, GloVe, and stacked autoencoder, while providing clinically meaningful interpretation.
Filed under: Big Data | Mining Rich Data Types