Identifying COVID-19 Outbreaks From Contact-Tracing Interview Forms for Public Health Departments: Development of a Natural Language Processing Pipeline.

Journal: JMIR public health and surveillance
PMID: 35144241

Abstract

BACKGROUND: In Wisconsin, COVID-19 case interview forms contain free-text fields that need to be mined to identify potential outbreaks for targeted policy making. We developed an automated pipeline to ingest the free text into a pretrained neural language model to identify businesses and facilities as outbreaks.

Authors

  • John Caskey
    Department of Medicine, University of Wisconsin, Madison, USA.
  • Iain L McConnell
    University of Wisconsin-Madison, Madison, WI, United States.
  • Madeline Oguss
    Department of Medicine, University of Wisconsin, Madison, USA.
  • Dmitriy Dligach
    Department of Public Health Sciences, Stritch School of Medicine, Loyola University Chicago, Maywood, IL.
  • Rachel Kulikoff
    Public Health Madison & Dane County, Madison, WI, United States.
  • Brittany Grogan
    Public Health Madison & Dane County, Madison, WI, United States.
  • Crystal Gibson
    Public Health Madison & Dane County, Madison, WI, United States.
  • Elizabeth Wimmer
    State of Wisconsin Department of Health Services, Madison, WI, United States.
  • Traci E DeSalvo
    State of Wisconsin Department of Health Services, Madison, WI, United States.
  • Edwin E Nyakoe-Nyasani
    State of Wisconsin Department of Health Services, Madison, WI, United States.
  • Matthew M Churpek
    Department of Medicine, University of Wisconsin-Madison, Madison, WI, United States.
  • Majid Afshar
    Loyola University Chicago, Chicago, IL.

Keywords

External Resources

Popular Topics
Recent Journals