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

doi:10.1109/ICHI52183.2021.00096

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 proceeding › Conference contribution

1 Scopus citations

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 language	English (US)
Title of host publication	Proceedings - 2021 IEEE 9th International Conference on Healthcare Informatics, ISCHI 2021
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	513-514
Number of pages	2
ISBN (Electronic)	9781665401326
DOIs	https://doi.org/10.1109/ICHI52183.2021.00096
State	Published - Aug 2021
Event	9th IEEE International Conference on Healthcare Informatics, ISCHI 2021 - Virtual, Victoria, Canada Duration: Aug 9 2021 → Aug 12 2021

Publication series

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

Conference

Conference	9th IEEE International Conference on Healthcare Informatics, ISCHI 2021
Country/Territory	Canada
City	Virtual, Victoria
Period	8/9/21 → 8/12/21

Bibliographical note

Publisher Copyright:
© 2021 IEEE.

Keywords

ADRD
BERT
Dietary supplements
EHR
MCI
Natural language processing

Publisher link

10.1109/ICHI52183.2021.00096

Find It

Find It at U of M Libraries

Cite this

Zhou, S., Schutte, D., Xing, A., Chen, J., Wolfson, J., He, Z., Yu, F., & Zhang, R. (2021). Identification of Dietary Supplement Use from Electronic Health Records Using Transformer-based Language Models. In Proceedings - 2021 IEEE 9th International Conference on Healthcare Informatics, ISCHI 2021 (pp. 513-514). (Proceedings - 2021 IEEE 9th International Conference on Healthcare Informatics, ISCHI 2021). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICHI52183.2021.00096

Identification of Dietary Supplement Use from Electronic Health Records Using Transformer-based Language Models. / Zhou, Sicheng; Schutte, Dalton; Xing, Aiwen et al.
Proceedings - 2021 IEEE 9th International Conference on Healthcare Informatics, ISCHI 2021. Institute of Electrical and Electronics Engineers Inc., 2021. p. 513-514 (Proceedings - 2021 IEEE 9th International Conference on Healthcare Informatics, ISCHI 2021).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Zhou, S, Schutte, D, Xing, A, Chen, J, Wolfson, J, He, Z, Yu, F & Zhang, R 2021, Identification of Dietary Supplement Use from Electronic Health Records Using Transformer-based Language Models. in Proceedings - 2021 IEEE 9th International Conference on Healthcare Informatics, ISCHI 2021. Proceedings - 2021 IEEE 9th International Conference on Healthcare Informatics, ISCHI 2021, Institute of Electrical and Electronics Engineers Inc., pp. 513-514, 9th IEEE International Conference on Healthcare Informatics, ISCHI 2021, Virtual, Victoria, Canada, 8/9/21. https://doi.org/10.1109/ICHI52183.2021.00096

Zhou S, Schutte D, Xing A, Chen J, Wolfson J, He Z et al. Identification of Dietary Supplement Use from Electronic Health Records Using Transformer-based Language Models. In Proceedings - 2021 IEEE 9th International Conference on Healthcare Informatics, ISCHI 2021. Institute of Electrical and Electronics Engineers Inc. 2021. p. 513-514. (Proceedings - 2021 IEEE 9th International Conference on Healthcare Informatics, ISCHI 2021). doi: 10.1109/ICHI52183.2021.00096

Zhou, Sicheng ; Schutte, Dalton ; Xing, Aiwen et al. / Identification of Dietary Supplement Use from Electronic Health Records Using Transformer-based Language Models. Proceedings - 2021 IEEE 9th International Conference on Healthcare Informatics, ISCHI 2021. Institute of Electrical and Electronics Engineers Inc., 2021. pp. 513-514 (Proceedings - 2021 IEEE 9th International Conference on Healthcare Informatics, ISCHI 2021).

@inproceedings{d26b34ce287441029f3334749af121c8,

title = "Identification of Dietary Supplement Use from Electronic Health Records Using Transformer-based Language Models",

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.",

keywords = "ADRD, BERT, Dietary supplements, EHR, MCI, Natural language processing",

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

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 9th IEEE International Conference on Healthcare Informatics, ISCHI 2021 ; Conference date: 09-08-2021 Through 12-08-2021",

year = "2021",

month = aug,

doi = "10.1109/ICHI52183.2021.00096",

language = "English (US)",

series = "Proceedings - 2021 IEEE 9th International Conference on Healthcare Informatics, ISCHI 2021",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "513--514",

booktitle = "Proceedings - 2021 IEEE 9th International Conference on Healthcare Informatics, ISCHI 2021",

}

TY - GEN

T1 - Identification of Dietary Supplement Use from Electronic Health Records Using Transformer-based Language Models

AU - Zhou, Sicheng

AU - Schutte, Dalton

AU - Xing, Aiwen

AU - Chen, Jiyang

AU - Wolfson, Julian

AU - He, Zhe

AU - Yu, Fang

AU - Zhang, Rui

PY - 2021/8

Y1 - 2021/8

N2 - 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.

AB - 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.

KW - ADRD

KW - BERT

KW - Dietary supplements

KW - EHR

KW - MCI

KW - Natural language processing

UR - http://www.scopus.com/inward/record.url?scp=85118133465&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85118133465&partnerID=8YFLogxK

U2 - 10.1109/ICHI52183.2021.00096

DO - 10.1109/ICHI52183.2021.00096

M3 - Conference contribution

AN - SCOPUS:85118133465

T3 - Proceedings - 2021 IEEE 9th International Conference on Healthcare Informatics, ISCHI 2021

SP - 513

EP - 514

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

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 9th IEEE International Conference on Healthcare Informatics, ISCHI 2021

Y2 - 9 August 2021 through 12 August 2021

ER -

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

Abstract

Publication series

Conference

Bibliographical note

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this