IDEAS home Printed from https://ideas.repec.org/a/spr/scient/v125y2020i3d10.1007_s11192-020-03648-6.html
   My bibliography  Save this article

Automatic document screening of medical literature using word and text embeddings in an active learning setting

Author

Listed:
  • Andres Carvallo

    (Pontificia Universidad Catolica de Chile)

  • Denis Parra

    (Pontificia Universidad Catolica de Chile)

  • Hans Lobel

    (Pontificia Universidad Catolica de Chile)

  • Alvaro Soto

    (Pontificia Universidad Catolica de Chile)

Abstract

Document screening is a fundamental task within Evidence-based Medicine (EBM), a practice that provides scientific evidence to support medical decisions. Several approaches have tried to reduce physicians’ workload of screening and labeling vast amounts of documents to answer clinical questions. Previous works tried to semi-automate document screening, reporting promising results, but their evaluation was conducted on small datasets, which hinders generalization. Moreover, recent works in natural language processing have introduced neural language models, but none have compared their performance in EBM. In this paper, we evaluate the impact of several document representations such as TF-IDF along with neural language models (BioBERT, BERT, Word2Vec, and GloVe) on an active learning-based setting for document screening in EBM. Our goal is to reduce the number of documents that physicians need to label to answer clinical questions. We evaluate these methods using both a small challenging dataset (CLEF eHealth 2017) as well as a larger one but easier to rank (Epistemonikos). Our results indicate that word as well as textual neural embeddings always outperform the traditional TF-IDF representation. When comparing among neural and textual embeddings, in the CLEF eHealth dataset the models BERT and BioBERT yielded the best results. On the larger dataset, Epistemonikos, Word2Vec and BERT were the most competitive, showing that BERT was the most consistent model across different corpuses. In terms of active learning, an uncertainty sampling strategy combined with a logistic regression achieved the best performance overall, above other methods under evaluation, and in fewer iterations. Finally, we compared the results of evaluating our best models, trained using active learning, with other authors methods from CLEF eHealth, showing better results in terms of work saved for physicians in the document-screening task.

Suggested Citation

  • Andres Carvallo & Denis Parra & Hans Lobel & Alvaro Soto, 2020. "Automatic document screening of medical literature using word and text embeddings in an active learning setting," Scientometrics, Springer;Akadémiai Kiadó, vol. 125(3), pages 3047-3084, December.
  • Handle: RePEc:spr:scient:v:125:y:2020:i:3:d:10.1007_s11192-020-03648-6
    DOI: 10.1007/s11192-020-03648-6
    as

    Download full text from publisher

    File URL: http://link.springer.com/10.1007/s11192-020-03648-6
    File Function: Abstract
    Download Restriction: Access to the full text of the articles in this series is restricted.

    File URL: https://libkey.io/10.1007/s11192-020-03648-6?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Julian H Elliott & Tari Turner & Ornella Clavisi & James Thomas & Julian P T Higgins & Chris Mavergames & Russell L Gruen, 2014. "Living Systematic Reviews: An Emerging Opportunity to Narrow the Evidence-Practice Gap," PLOS Medicine, Public Library of Science, vol. 11(2), pages 1-6, February.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Leihong Wu & Syed Ali & Heather Ali & Tyrone Brock & Joshua Xu & Weida Tong, 2022. "NeuroCORD: A Language Model to Facilitate COVID-19-Associated Neurological Disorder Studies," IJERPH, MDPI, vol. 19(16), pages 1-10, August.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Manh-Toan Ho & Ngoc-Thang B. Le & Manh-Tung Ho & Quan-Hoang Vuong, 2022. "A bibliometric review on development economics research in Vietnam from 2008 to 2020," Quality & Quantity: International Journal of Methodology, Springer, vol. 56(5), pages 2939-2969, October.
    2. Guillaume Cabanac & Theodora Oikonomidi & Isabelle Boutron, 2021. "Day-to-day discovery of preprint–publication links," Scientometrics, Springer;Akadémiai Kiadó, vol. 126(6), pages 5285-5304, June.
    3. Maurizio Sajeva & Marjo Maidell & Jonne Kotta, 2020. "A Participatory Geospatial Toolkit for Science Integration and Knowledge Transfer Informing SDGs Based Governance and Decision Making," Sustainability, MDPI, vol. 12(19), pages 1-19, September.
    4. Radoslaw Panczak & Elin Charles-Edwards & Jonathan Corcoran, 2020. "Estimating temporary populations: a systematic review of the empirical literature," Palgrave Communications, Palgrave Macmillan, vol. 6(1), pages 1-10, June.
    5. Sheila Keay & Zvonimir Poljak & Mackenzie Klapwyk & Annette O’Connor & Robert M Friendship & Terri L O’Sullivan & Jan M Sargeant, 2020. "Influenza A virus vaccine research conducted in swine from 1990 to May 2018: A scoping review," PLOS ONE, Public Library of Science, vol. 15(7), pages 1-27, July.
    6. Steven Kwasi Korang & Elena von Rohden & Areti Angeliki Veroniki & Giok Ong & Owen Ngalamika & Faiza Siddiqui & Sophie Juul & Emil Eik Nielsen & Joshua Buron Feinberg & Johanne Juul Petersen & Christi, 2022. "Vaccines to prevent COVID-19: A living systematic review with Trial Sequential Analysis and network meta-analysis of randomized clinical trials," PLOS ONE, Public Library of Science, vol. 17(1), pages 1-23, January.
    7. Julia H. Littell & Sarah Young & Therese D. Pigott & M. Antonia Biggs & Trine Munk‐Olsen & Julia R. Steinberg, 2024. "PROTOCOL: Abortion and mental health outcomes: A systematic review and meta‐analysis," Campbell Systematic Reviews, John Wiley & Sons, vol. 20(2), June.
    8. Ruth Stewart & Harsha Dayal & Laurenz Langer & Carina van Rooyen, 2022. "Transforming evidence for policy: do we have the evidence generation house in order?," Palgrave Communications, Palgrave Macmillan, vol. 9(1), pages 1-5, December.
    9. Ruth Stewart & Harsha Dayal & Laurenz Langer & Carina van Rooyen, 2019. "The evidence ecosystem in South Africa: growing resilience and institutionalisation of evidence use," Palgrave Communications, Palgrave Macmillan, vol. 5(1), pages 1-12, December.
    10. Marion Schmidt & Wolfgang Kircheis & Arno Simons & Martin Potthast & Benno Stein, 2023. "A diachronic perspective on citation latency in Wikipedia articles on CRISPR/Cas-9: an exploratory case study," Scientometrics, Springer;Akadémiai Kiadó, vol. 128(6), pages 3649-3673, June.
    11. Ho, Manh-Toan, 2020. "The rise of research on development economics in Vietnam: Analyses and implications for the public and policymakers from SSHPA 2008-2020 dataset," Thesis Commons msy6e, Center for Open Science.
    12. , Aisdl, 2020. "The rise of research on development economics in Vietnam: Analyses and implications for the public and policymakers from SSHPA 2008-2020 dataset," OSF Preprints 9nbyr, Center for Open Science.
    13. Alice Freiberg & Melanie Schubert & Karla Romero Starke & Janice Hegewald & Andreas Seidler, 2021. "A Rapid Review on the Influence of COVID-19 Lockdown and Quarantine Measures on Modifiable Cardiovascular Risk Factors in the General Population," IJERPH, MDPI, vol. 18(16), pages 1-46, August.
    14. Danyang Li & Liwei Zhang & Xin Yue & Daniel Memmert & Yeqin Zhang, 2022. "Effect of Attentional Focus on Sprint Performance: A Meta-Analysis," IJERPH, MDPI, vol. 19(10), pages 1-13, May.
    15. Gillian L Currie & Helena N Angel-Scott & Lesley Colvin & Fala Cramond & Kaitlyn Hair & Laila Khandoker & Jing Liao & Malcolm Macleod & Sarah K McCann & Rosie Morland & Nicki Sherratt & Robert Stewart, 2019. "Animal models of chemotherapy-induced peripheral neuropathy: A machine-assisted systematic review and meta-analysis," PLOS Biology, Public Library of Science, vol. 17(5), pages 1-34, May.
    16. Fiona Campbell & Ruth Wong & Jennifer L. Llewellyen & Akvile Stoniute & Fiona Pearson & Melissa Bond, 2024. "PROTOCOL: Methods used in the development, production and updating of evidence and gap maps: A scoping review," Campbell Systematic Reviews, John Wiley & Sons, vol. 20(2), June.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:spr:scient:v:125:y:2020:i:3:d:10.1007_s11192-020-03648-6. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Sonal Shukla or Springer Nature Abstracting and Indexing (email available below). General contact details of provider: http://www.springer.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.