Identifying diabetes in clinical notes in Hebrew: A novel text classification approach based on word embedding

Maxim Topaz; Ludmila Murga; Chagai Grossman; Daniella Daliyot; Shlomit Jacobson; Noa Rozendorn; Eyal Zimlichman; Nadav Furie

doi:10.3233/SHTI190250

Identifying diabetes in clinical notes in Hebrew: A novel text classification approach based on word embedding

Maxim Topaz
, Ludmila Murga
, Chagai Grossman
, Daniella Daliyot
, Shlomit Jacobson
, Noa Rozendorn
, Eyal Zimlichman
, Nadav Furie

Columbia University
VNS Health
University of Haifa
Sheba Medical Center at Tel Hashomer

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

6 Scopus citations

Abstract

NimbleMiner is a word embedding-based, language-agnostic natural language processing system for clinical text classification. Previously, NimbleMiner was applied in English and this study applied NimbleMiner on a large sample of inpatient clinical notes in Hebrew to identify instances of diabetes mellitus. The study data included 521,278 clinical notes (one admission and one discharge note per patient) for 268,664 hospital admissions to medical-surgical units of a large hospital in Israel. NimbleMiner achieved overall good performance (F-score =.94) when tested on a gold standard human annotated dataset of 800 clinical notes. We found 15% more patients with diabetes mentioned in the clinical notes compared with diagnoses data. Our findings about underreporting of diabetes in the coded diagnoses data highlight the urgent need for tools and algorithms that will help busy providers identify a range of useful information, like having a diabetes.

Original language	English
Title of host publication	MEDINFO 2019
Subtitle of host publication	Health and Wellbeing e-Networks for All - Proceedings of the 17th World Congress on Medical and Health Informatics
Editors	Brigitte Seroussi, Lucila Ohno-Machado, Lucila Ohno-Machado, Brigitte Seroussi
Publisher	IOS Press
Pages	393-397
Number of pages	5
ISBN (Electronic)	9781643680026
DOIs	https://doi.org/10.3233/SHTI190250
State	Published - 21 Aug 2019
Externally published	Yes
Event	17th World Congress on Medical and Health Informatics, MEDINFO 2019 - Lyon, France Duration: 25 Aug 2019 → 30 Aug 2019

Publication series

Name	Studies in Health Technology and Informatics
Volume	264
ISSN (Print)	0926-9630
ISSN (Electronic)	1879-8365

Conference

Conference	17th World Congress on Medical and Health Informatics, MEDINFO 2019
Country/Territory	France
City	Lyon
Period	25/08/19 → 30/08/19

Bibliographical note

Publisher Copyright:
© 2019 International Medical Informatics Association (IMIA) and IOS Press.

Funding

Funding for this work was provided through Sheba Innovation Fund.

Funders
Sheba Innovation Fund

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Diabetes
Natural language processing
Text classification

Access to Document

10.3233/SHTI190250

Cite this

Topaz, M., Murga, L., Grossman, C., Daliyot, D., Jacobson, S., Rozendorn, N., Zimlichman, E., & Furie, N. (2019). Identifying diabetes in clinical notes in Hebrew: A novel text classification approach based on word embedding. In B. Seroussi, L. Ohno-Machado, L. Ohno-Machado, & B. Seroussi (Eds.), MEDINFO 2019: Health and Wellbeing e-Networks for All - Proceedings of the 17th World Congress on Medical and Health Informatics (pp. 393-397). (Studies in Health Technology and Informatics; Vol. 264). IOS Press. https://doi.org/10.3233/SHTI190250

Topaz, Maxim ; Murga, Ludmila ; Grossman, Chagai et al. / Identifying diabetes in clinical notes in Hebrew : A novel text classification approach based on word embedding. MEDINFO 2019: Health and Wellbeing e-Networks for All - Proceedings of the 17th World Congress on Medical and Health Informatics. editor / Brigitte Seroussi ; Lucila Ohno-Machado ; Lucila Ohno-Machado ; Brigitte Seroussi. IOS Press, 2019. pp. 393-397 (Studies in Health Technology and Informatics).

@inproceedings{2eab7aa7b0e94c17a7e60bb2dd289b79,

title = "Identifying diabetes in clinical notes in Hebrew: A novel text classification approach based on word embedding",

abstract = "NimbleMiner is a word embedding-based, language-agnostic natural language processing system for clinical text classification. Previously, NimbleMiner was applied in English and this study applied NimbleMiner on a large sample of inpatient clinical notes in Hebrew to identify instances of diabetes mellitus. The study data included 521,278 clinical notes (one admission and one discharge note per patient) for 268,664 hospital admissions to medical-surgical units of a large hospital in Israel. NimbleMiner achieved overall good performance (F-score =.94) when tested on a gold standard human annotated dataset of 800 clinical notes. We found 15\% more patients with diabetes mentioned in the clinical notes compared with diagnoses data. Our findings about underreporting of diabetes in the coded diagnoses data highlight the urgent need for tools and algorithms that will help busy providers identify a range of useful information, like having a diabetes.",

keywords = "Diabetes, Natural language processing, Text classification",

author = "Maxim Topaz and Ludmila Murga and Chagai Grossman and Daniella Daliyot and Shlomit Jacobson and Noa Rozendorn and Eyal Zimlichman and Nadav Furie",

note = "Publisher Copyright: {\textcopyright} 2019 International Medical Informatics Association (IMIA) and IOS Press.; 17th World Congress on Medical and Health Informatics, MEDINFO 2019 ; Conference date: 25-08-2019 Through 30-08-2019",

year = "2019",

month = aug,

day = "21",

doi = "10.3233/SHTI190250",

language = "אנגלית",

series = "Studies in Health Technology and Informatics",

publisher = "IOS Press",

pages = "393--397",

editor = "Brigitte Seroussi and Lucila Ohno-Machado and Lucila Ohno-Machado and Brigitte Seroussi",

booktitle = "MEDINFO 2019",

address = "הולנד",

}

Topaz, M, Murga, L, Grossman, C, Daliyot, D, Jacobson, S, Rozendorn, N, Zimlichman, E & Furie, N 2019, Identifying diabetes in clinical notes in Hebrew: A novel text classification approach based on word embedding. in B Seroussi, L Ohno-Machado, L Ohno-Machado & B Seroussi (eds), MEDINFO 2019: Health and Wellbeing e-Networks for All - Proceedings of the 17th World Congress on Medical and Health Informatics. Studies in Health Technology and Informatics, vol. 264, IOS Press, pp. 393-397, 17th World Congress on Medical and Health Informatics, MEDINFO 2019, Lyon, France, 25/08/19. https://doi.org/10.3233/SHTI190250

Identifying diabetes in clinical notes in Hebrew: A novel text classification approach based on word embedding. / Topaz, Maxim; Murga, Ludmila; Grossman, Chagai et al.
MEDINFO 2019: Health and Wellbeing e-Networks for All - Proceedings of the 17th World Congress on Medical and Health Informatics. ed. / Brigitte Seroussi; Lucila Ohno-Machado; Lucila Ohno-Machado; Brigitte Seroussi. IOS Press, 2019. p. 393-397 (Studies in Health Technology and Informatics; Vol. 264).

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

TY - GEN

T1 - Identifying diabetes in clinical notes in Hebrew

T2 - 17th World Congress on Medical and Health Informatics, MEDINFO 2019

AU - Topaz, Maxim

AU - Murga, Ludmila

AU - Grossman, Chagai

AU - Daliyot, Daniella

AU - Jacobson, Shlomit

AU - Rozendorn, Noa

AU - Zimlichman, Eyal

AU - Furie, Nadav

PY - 2019/8/21

Y1 - 2019/8/21

N2 - NimbleMiner is a word embedding-based, language-agnostic natural language processing system for clinical text classification. Previously, NimbleMiner was applied in English and this study applied NimbleMiner on a large sample of inpatient clinical notes in Hebrew to identify instances of diabetes mellitus. The study data included 521,278 clinical notes (one admission and one discharge note per patient) for 268,664 hospital admissions to medical-surgical units of a large hospital in Israel. NimbleMiner achieved overall good performance (F-score =.94) when tested on a gold standard human annotated dataset of 800 clinical notes. We found 15% more patients with diabetes mentioned in the clinical notes compared with diagnoses data. Our findings about underreporting of diabetes in the coded diagnoses data highlight the urgent need for tools and algorithms that will help busy providers identify a range of useful information, like having a diabetes.

AB - NimbleMiner is a word embedding-based, language-agnostic natural language processing system for clinical text classification. Previously, NimbleMiner was applied in English and this study applied NimbleMiner on a large sample of inpatient clinical notes in Hebrew to identify instances of diabetes mellitus. The study data included 521,278 clinical notes (one admission and one discharge note per patient) for 268,664 hospital admissions to medical-surgical units of a large hospital in Israel. NimbleMiner achieved overall good performance (F-score =.94) when tested on a gold standard human annotated dataset of 800 clinical notes. We found 15% more patients with diabetes mentioned in the clinical notes compared with diagnoses data. Our findings about underreporting of diabetes in the coded diagnoses data highlight the urgent need for tools and algorithms that will help busy providers identify a range of useful information, like having a diabetes.

KW - Diabetes

KW - Natural language processing

KW - Text classification

UR - https://www.scopus.com/pages/publications/85071428695

U2 - 10.3233/SHTI190250

DO - 10.3233/SHTI190250

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

C2 - 31437952

AN - SCOPUS:85071428695

T3 - Studies in Health Technology and Informatics

SP - 393

EP - 397

BT - MEDINFO 2019

A2 - Seroussi, Brigitte

A2 - Ohno-Machado, Lucila

A2 - Seroussi, Brigitte

PB - IOS Press

Y2 - 25 August 2019 through 30 August 2019

ER -

Topaz M, Murga L, Grossman C, Daliyot D, Jacobson S, Rozendorn N et al. Identifying diabetes in clinical notes in Hebrew: A novel text classification approach based on word embedding. In Seroussi B, Ohno-Machado L, Ohno-Machado L, Seroussi B, editors, MEDINFO 2019: Health and Wellbeing e-Networks for All - Proceedings of the 17th World Congress on Medical and Health Informatics. IOS Press. 2019. p. 393-397. (Studies in Health Technology and Informatics). doi: 10.3233/SHTI190250

Identifying diabetes in clinical notes in Hebrew: A novel text classification approach based on word embedding

Abstract

Publication series

Conference

Bibliographical note

Funding

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this