Using automation to produce a ‘living map’ of the COVID-19 research literature

Ian Shemilt; Anneliese Arno; James Thomas; Theo Lorenc; Claire Khouja; Gary Raine; Katy Sutcliffe; Preethy D'Souza; Kath Wright; Amanda Sowden

doi:10.32384/jeahil17469

Using automation to produce a ‘living map’ of the COVID-19 research literature

Ian Shemilt, Anneliese Arno, James Thomas, Theo Lorenc, Claire Khouja, Gary Raine, Katy Sutcliffe, Preethy D'Souza, Kath Wright, Amanda Sowden

Centre for Reviews and Dissemination

Research output: Contribution to journal › Article › peer-review

Abstract

The COVID-19 pandemic has disrupted life worldwide and presented unique challenges in the health evidencesynthesis space. The urgent nature of the pandemic required extreme rapidity for keeping track of research, andthis presented a unique opportunity for long-proposed automation systems to be deployed and evaluated. Wecompared the use of novel automation technologies with conventional manual screening; and Microsoft AcademicGraph (MAG) with the MEDLINE and Embase databases locating the emerging research evidence. We foundthat a new workflow involving machine learning to identify relevant research in MAG achieved a much higherrecall with lower manual effort than using conventional approaches.

Original language	English
Pages (from-to)	11-15
Number of pages	5
Journal	Journal of the European Association for Health Information and Libraries
Volume	17
Issue number	2
DOIs	https://doi.org/10.32384/jeahil17469
Publication status	Published - 23 Jun 2021

Bibliographical note

Access to Document

10.32384/jeahil17469Licence: CC BY

document
© 2021, The Author(s).
Final published version, 1.5 MBLicence: CC BY

http://ojs.eahil.eu/ojs/index.php/JEAHIL/article/view/469

Cite this

@article{f8180fed8732474cb0451947aff8bb5f,

title = "Using automation to produce a {\textquoteleft}living map{\textquoteright} of the COVID-19 research literature",

abstract = "The COVID-19 pandemic has disrupted life worldwide and presented unique challenges in the health evidencesynthesis space. The urgent nature of the pandemic required extreme rapidity for keeping track of research, andthis presented a unique opportunity for long-proposed automation systems to be deployed and evaluated. Wecompared the use of novel automation technologies with conventional manual screening; and Microsoft AcademicGraph (MAG) with the MEDLINE and Embase databases locating the emerging research evidence. We foundthat a new workflow involving machine learning to identify relevant research in MAG achieved a much higherrecall with lower manual effort than using conventional approaches.",

author = "Ian Shemilt and Anneliese Arno and James Thomas and Theo Lorenc and Claire Khouja and Gary Raine and Katy Sutcliffe and Preethy D'Souza and Kath Wright and Amanda Sowden",

note = "{\textcopyright} 2021, The Author(s).",

year = "2021",

month = jun,

day = "23",

doi = "10.32384/jeahil17469",

language = "English",

volume = "17",

pages = "11--15",

journal = "Journal of the European Association for Health Information and Libraries",

issn = "1841-0715",

number = "2",

}

TY - JOUR

T1 - Using automation to produce a ‘living map’ of the COVID-19 research literature

AU - Shemilt, Ian

AU - Arno, Anneliese

AU - Thomas, James

AU - Lorenc, Theo

AU - Khouja, Claire

AU - Raine, Gary

AU - Sutcliffe, Katy

AU - D'Souza, Preethy

AU - Wright, Kath

AU - Sowden, Amanda

PY - 2021/6/23

Y1 - 2021/6/23

N2 - The COVID-19 pandemic has disrupted life worldwide and presented unique challenges in the health evidencesynthesis space. The urgent nature of the pandemic required extreme rapidity for keeping track of research, andthis presented a unique opportunity for long-proposed automation systems to be deployed and evaluated. Wecompared the use of novel automation technologies with conventional manual screening; and Microsoft AcademicGraph (MAG) with the MEDLINE and Embase databases locating the emerging research evidence. We foundthat a new workflow involving machine learning to identify relevant research in MAG achieved a much higherrecall with lower manual effort than using conventional approaches.

AB - The COVID-19 pandemic has disrupted life worldwide and presented unique challenges in the health evidencesynthesis space. The urgent nature of the pandemic required extreme rapidity for keeping track of research, andthis presented a unique opportunity for long-proposed automation systems to be deployed and evaluated. Wecompared the use of novel automation technologies with conventional manual screening; and Microsoft AcademicGraph (MAG) with the MEDLINE and Embase databases locating the emerging research evidence. We foundthat a new workflow involving machine learning to identify relevant research in MAG achieved a much higherrecall with lower manual effort than using conventional approaches.

U2 - 10.32384/jeahil17469

DO - 10.32384/jeahil17469

M3 - Article

SN - 1841-0715

VL - 17

SP - 11

EP - 15

JO - Journal of the European Association for Health Information and Libraries

JF - Journal of the European Association for Health Information and Libraries

IS - 2

ER -