Automated information extraction from free-text medical documents for stroke key performance indicators: a pilot study.

Journal: Internal medicine journal
Published Date: Feb 1, 2022

Abstract

Automated information extraction might be able to assist with the collection of stroke key performance indicators (KPI). The feasibility of using natural language processing for classification-based KPI and datetime field extraction was assessed. Using free-text discharge summaries, random forest models achieved high levels of performance in classification tasks (area under the receiver operator curve 0.95-1.00). The datetime field extraction method was successful in 29 of 43 (67.4%) cases. Further studies are indicated.

Authors

  • Stephen Bacchi
    Faculty of Health and Medical Sciences, Adelaide Medical School, University of Adelaide, Adelaide, SA 5000 Australia.
  • Sam Gluck
    Royal Adelaide Hospital, Adelaide, South Australia, Australia.
  • Simon Koblar
    Neurology Department, Royal Adelaide Hospital, Port Road, Adelaide, SA, 5000, Australia.
  • Jim Jannes
    From the Royal Adelaide Hospital, Adelaide, Australia (S.B., L.O.-R., T.K., S.P., J.J.).
  • Timothy Kleinig
    From the Royal Adelaide Hospital, Adelaide, Australia (S.B., L.O.-R., T.K., S.P., J.J.).

Keywords

External Resources

Popular Topics
Recent Journals