Clinical Concept Embeddings Learned from Massive Sources of Multimodal Medical Data

Andrew L. Beam1,†,*, Benjamin Kompa2,†, Allen Schmaltz1, Inbar Fried3, Griffin Weber2, Nathan Palmer2, Xu Shi1, Tianxi Cai1, Isaac S. Kohane2


1Harvard T.H. Chan School of Public Health
2Harvard Medical School
3University of North Carolina School of Medicine
Authors contributed equally to this work
*Corresponding author
Email: andrew beam@hms.harvard.edu

Pacific Symposium on Biocomputing 25:295-306(2020)

© 2020 World Scientific
Open Access chapter published by World Scientific Publishing Company and distributed under the terms of the Creative Commons Attribution (CC BY) 4.0 License.


Abstract

Word embeddings are a popular approach to unsupervised learning of word relationships that are widely used in natural language processing. In this article, we present a new set of embeddings for medical concepts learned using an extremely large collection of multimodal medical data. Leaning on recent theoretical insights, we demonstrate how an insurance claims database of 60 million members, a collection of 20 million clinical notes, and 1.7 million full text biomedical journal articles can be combined to embed concepts into a common space, resulting in the largest ever set of embeddings for 108,477 medical concepts. To evaluate our approach, we present a new benchmark methodology based on statistical power specifically designed to test embeddings of medical concepts. Our approach, called cui2vec, attains state-of-the-art performance relative to previous methods in most instances. Finally, we provide a downloadable set of pre-trained embeddings for other researchers to use, as well as an online tool for interactive exploration of the cui2vec embeddings.


[Full-Text PDF] [PSB Home Page]