Literature DB >> 30961579

Time-sensitive clinical concept embeddings learned from large electronic health records.

Yang Xiang1, Jun Xu1, Yuqi Si1, Zhiheng Li1,2, Laila Rasmy1, Yujia Zhou1, Firat Tiryaki1, Fang Li1, Yaoyun Zhang1, Yonghui Wu3, Xiaoqian Jiang1, Wenjin Jim Zheng1, Degui Zhi1, Cui Tao1, Hua Xu4.   

Abstract

BACKGROUND: Learning distributional representation of clinical concepts (e.g., diseases, drugs, and labs) is an important research area of deep learning in the medical domain. However, many existing relevant methods do not consider temporal dependencies along the longitudinal sequence of a patient's records, which may lead to incorrect selection of contexts.
METHODS: To address this issue, we extended three popular concept embedding learning methods: word2vec, positive pointwise mutual information (PPMI) and FastText, to consider time-sensitive information. We then trained them on a large electronic health records (EHR) database containing about 50 million patients to generate concept embeddings and evaluated them for both intrinsic evaluations focusing on concept similarity measure and an extrinsic evaluation to assess the use of generated concept embeddings in the task of predicting disease onset.
RESULTS: Our experiments show that embeddings learned from information within one visit (time window zero) improve performance on the concept similarity measure and the FastText algorithm usually had better performance than the other two algorithms. For the predictive modeling task, the optimal result was achieved by word2vec embeddings with a 30-day sliding window.
CONCLUSIONS: Considering time constraints are important in training clinical concept embeddings. We expect they can benefit a series of downstream applications.

Entities:  

Keywords:  Clinical concept embedding; Concept similarity; Distributional representation; Electronic medical records; Predictive modeling; Time sensitive concept embedding

Mesh:

Year:  2019        PMID: 30961579      PMCID: PMC6454598          DOI: 10.1186/s12911-019-0766-3

Source DB:  PubMed          Journal:  BMC Med Inform Decis Mak        ISSN: 1472-6947            Impact factor:   2.796


  2 in total

1.  Electronic health records vs Medicaid claims: completeness of diabetes preventive care data in community health centers.

Authors:  Jennifer E Devoe; Rachel Gold; Patti McIntire; Jon Puro; Susan Chauvie; Charles A Gallia
Journal:  Ann Fam Med       Date:  2011 Jul-Aug       Impact factor: 5.166

2.  A study of generalizability of recurrent neural network-based predictive models for heart failure onset risk using a large and heterogeneous EHR data set.

Authors:  Laila Rasmy; Yonghui Wu; Ningtao Wang; Xin Geng; W Jim Zheng; Fei Wang; Hulin Wu; Hua Xu; Degui Zhi
Journal:  J Biomed Inform       Date:  2018-06-15       Impact factor: 6.317

  2 in total
  5 in total

1.  Representation of EHR data for predictive modeling: a comparison between UMLS and other terminologies.

Authors:  Laila Rasmy; Firat Tiryaki; Yujia Zhou; Yang Xiang; Cui Tao; Hua Xu; Degui Zhi
Journal:  J Am Med Inform Assoc       Date:  2020-10-01       Impact factor: 4.497

Review 2.  Artificial intelligence and computer simulation models in critical illness.

Authors:  Amos Lal; Yuliya Pinevich; Ognjen Gajic; Vitaly Herasevich; Brian Pickering
Journal:  World J Crit Care Med       Date:  2020-06-05

3.  BioConceptVec: Creating and evaluating literature-based biomedical concept embeddings on a large scale.

Authors:  Qingyu Chen; Kyubum Lee; Shankai Yan; Sun Kim; Chih-Hsuan Wei; Zhiyong Lu
Journal:  PLoS Comput Biol       Date:  2020-04-23       Impact factor: 4.475

4.  Exploiting hierarchy in medical concept embedding.

Authors:  Anthony Finch; Alexander Crowell; Mamta Bhatia; Pooja Parameshwarappa; Yung-Chieh Chang; Jose Martinez; Michael Horberg
Journal:  JAMIA Open       Date:  2021-03-16

5.  A comparison of attentional neural network architectures for modeling with electronic medical records.

Authors:  Anthony Finch; Alexander Crowell; Yung-Chieh Chang; Pooja Parameshwarappa; Jose Martinez; Michael Horberg
Journal:  JAMIA Open       Date:  2021-08-12
  5 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.