Identification of Dietary Supplement Use from Electronic Health Records Using Transformer-based Language Models

Sicheng Zhou, Dalton Schutte, Aiwen Xing, Jiyang Chen, Julian Wolfson, Zhe He, Fang Yu, Rui Zhang

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

Abstract

The roles of dietary supplement (DS) usage on disease progression of patients with cognitive impairments remain unclear. Transformed-based language models were trained to identify DS use status from clinical notes among patients with Alzheimer's disease and related dementias (ADRD). The best name entity recognition for DS achieved F1-score is 0.964 and the PubMed BERT based use status classifier achieved the weighted F1-score of 0.879. Integrating with DS use from medication table, we identified totally 125 unique DS among patients with mild cognitive impairment (MCI) only and 108 unique DS among patients who progressed to ADRD.

Original languageEnglish (US)
Title of host publicationProceedings - 2021 IEEE 9th International Conference on Healthcare Informatics, ISCHI 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages513-514
Number of pages2
ISBN (Electronic)9781665401326
DOIs
StatePublished - Aug 2021
Event9th IEEE International Conference on Healthcare Informatics, ISCHI 2021 - Virtual, Victoria, Canada
Duration: Aug 9 2021Aug 12 2021

Publication series

NameProceedings - 2021 IEEE 9th International Conference on Healthcare Informatics, ISCHI 2021

Conference

Conference9th IEEE International Conference on Healthcare Informatics, ISCHI 2021
Country/TerritoryCanada
CityVirtual, Victoria
Period8/9/218/12/21

Keywords

  • ADRD
  • BERT
  • Dietary supplements
  • EHR
  • MCI
  • Natural language processing

ASJC Scopus subject areas

  • Modeling and Simulation
  • Health Informatics
  • Health(social science)

Fingerprint

Dive into the research topics of 'Identification of Dietary Supplement Use from Electronic Health Records Using Transformer-based Language Models'. Together they form a unique fingerprint.

Cite this