Clinical Concept Embeddings Learned from Massive Sources of Multimodal Medical Data

TL;DR

This paper introduces cui2vec, a large set of medical concept embeddings learned from multimodal data sources, demonstrating superior performance and providing tools for research and exploration.

Contribution

It presents the largest medical concept embeddings learned from multimodal data and introduces a new benchmark for evaluating such embeddings.

Findings

Achieved state-of-the-art performance on medical concept embedding tasks.

Created the largest set of embeddings for over 108,000 medical concepts.

Provided accessible tools and pre-trained embeddings for the research community.

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