EUVIMEDEUVIMED entdecken
Crossref

Predicting the Utility of Scientific Articles for Emerging Pandemics Using Their Titles and Natural Language Processing

Kinga Dobolyi, Sidra Hussain, Grady McPeak

Disaster Medicine and Public Health Preparedness · 2024

DOI: 10.1017/dmp.2024.109 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Disaster Medicine and Public Health Preparedness, 2024. Verfasst von Kinga Dobolyi und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, George Washington University, Washington, DC, USA. Hauptthemen laut MEDLINE: Natural Language Processing, COVID-19, Pandemics. Die Arbeit nennt 16 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

Not all scientific publications are equally useful to policy-makers tasked with mitigating the spread and impact of diseases, especially at the start of novel epidemics and pandemics. The urgent need for actionable, evidence-based information is paramount, but the nature of preprint and peer-reviewed articles published during these times is often at odds with such goals. For example, a lack of novel results and a focus on opinions rather than evidence were common in coronavirus disease (COVID-19) publications at the start of the pandemic in 2019. In this work, we seek to automatically judge the utility of these scientific articles, from a public health policy making persepctive, using only their titles.

Methods

Deep learning natural language processing (NLP) models were trained on scientific COVID-19 publication titles from the CORD-19 dataset and evaluated against expert-curated COVID-19 evidence to measure their real-world feasibility at screening these scientific publications in an automated manner.

Results

This work demonstrates that it is possible to judge the utility of COVID-19 scientific articles, from a public health policy-making perspective, based on their title alone, using deep natural language processing (NLP) models.

Conclusions

NLP models can be successfully trained on scienticic articles and used by public health experts to triage and filter the hundreds of new daily publications on novel diseases such as COVID-19 at the start of pandemics.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Natural Language ProcessingCOVID-19PandemicsHumansSARS-CoV-2Deep LearningPublications

Stichwörter der Autor:innen

natural language processingpandemicpolicypublic healthscientific articlesutility

Autor:innen und Institutionen

  • Department of Computer Science, George Washington University, Washington, DC, USA.

Zitieren

APA

Dobolyi, K., Hussain, S., & McPeak, G. (2024). Predicting the Utility of Scientific Articles for Emerging Pandemics Using Their Titles and Natural Language Processing. Disaster Medicine and Public Health Preparedness. https://doi.org/10.1017/dmp.2024.109

Vancouver

Dobolyi K, Hussain S, McPeak G. Predicting the Utility of Scientific Articles for Emerging Pandemics Using Their Titles and Natural Language Processing. Disaster Medicine and Public Health Preparedness. 2024. doi:10.1017/dmp.2024.109

BibTeX
@article{Dobolyi2024,
  author = {Dobolyi, Kinga and Hussain, Sidra and McPeak, Grady},
  title = {Predicting the Utility of Scientific Articles for Emerging Pandemics Using Their Titles and Natural Language Processing},
  journal = {Disaster Medicine and Public Health Preparedness},
  year = {2024},
  doi = {10.1017/dmp.2024.109}
}
Kostenlos starten →