Med2Meta: Learning representations of medical concepts with meta-embeddings

Shaika Chowdhury, Chenwei Zhang, Philip S. Yu, Yuan Luo

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Distributed representations of medical concepts have been used to support downstream clinical tasks recently. Electronic Health Records (EHR) capture different aspects of patients' hospital encounters and serve as a rich source for augmenting clinical decision making by learning robust medical concept embeddings. However, the same medical concept can be recorded in different modalities (e.g., clinical notes, lab results) - with each capturing salient information unique to that modality - and a holistic representation calls for relevant feature ensemble from all information sources. We hypothesize that representations learned from heterogeneous data types would lead to performance enhancement on various clinical informatics and predictive modeling tasks. To this end, our proposed approach makes use of meta-embeddings, embeddings aggregated from learned embeddings. Firstly, modality-specific embeddings for each medical concept is learned with graph autoencoders. The ensemble of all the embeddings is then modeled as a meta-embedding learning problem to incorporate their correlating and complementary information through a joint reconstruction. Empirical results of our model on both quantitative and qualitative clinical evaluations have shown improvements over state-of-the-art embedding models, thus validating our hypothesis.

Original languageEnglish (US)
Title of host publicationHEALTHINF 2020 - 13th International Conference on Health Informatics, Proceedings; Part of 13th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2020
EditorsFederico Cabitza, Ana Fred, Hugo Gamboa
PublisherSciTePress
Pages369-376
Number of pages8
ISBN (Electronic)9789897583988
StatePublished - 2020
Event13th International Conference on Health Informatics, HEALTHINF 2020 - Part of 13th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2020 - Valletta, Malta
Duration: Feb 24 2020Feb 26 2020

Publication series

NameHEALTHINF 2020 - 13th International Conference on Health Informatics, Proceedings; Part of 13th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2020

Conference

Conference13th International Conference on Health Informatics, HEALTHINF 2020 - Part of 13th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2020
Country/TerritoryMalta
CityValletta
Period2/24/202/26/20

Keywords

  • Electronic health records
  • Graph neural networks
  • Meta-embeddings
  • Representation learning

ASJC Scopus subject areas

  • Biomedical Engineering
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Med2Meta: Learning representations of medical concepts with meta-embeddings'. Together they form a unique fingerprint.

Cite this