Unveiling Fall Risk Factors: Nurse-Driven Corpus Development for Natural Language Processing.

Journal: Studies in health technology and informatics
PMID: 39049286

Abstract

Hospital-acquired falls are a continuing clinical concern. The emergence of advanced analytical methods, including NLP, has created opportunities to leverage nurse-generated data, such as clinical notes, to better address the problem of falls. In this nurse-driven study, we employed an iterative process for expert manual annotation of RNs clinical notes to enable the training and testing of an NLP pipeline to extract factors related to falls. The resulting annotated data corpus had moderately high interrater reliability (F-score=0.74) and captured a breadth of clinical concepts for extraction with potential utility beyond patient falls. Further research is needed to determine which annotation tasks most benefit from nursing expert annotators, to optimize efficiency when tapping into the invaluable resource represented by the nursing workforce.

Authors

  • Ragnhildur I Bjarnadottir
    Department of Family, Community and Health Systems Science, College of Nursing, University of Florida, Gainesville, Florida, USA.
  • Yonghui Wu
    Department of Health Outcomes and Biomedical Informatics.
  • Urszula A Snigurska
    University of Florida, Gainesville, FL, USA.
  • Sarah E Ser
    University of Florida, Gainesville, FL, USA.
  • Laurence M Solberg
    GRECC, North Florida/South Georgia VHS, Gainesville, FL USA.
  • Kimberly A Martinez
    UF Health Shands Hospital, Gainesville, FL, USA.
  • Summer Bolin
    UF Health Shands Hospital, Gainesville, FL, USA.
  • Shannon E Dwarica
    UF Health Shands Hospital, Gainesville, FL, USA.
  • Elizabeth Dunn
    University of Florida, Gainesville, FL, USA.
  • Laurie J D Duckworth
    University of Florida, Gainesville, FL, USA.
  • Cxiwei Lou
    University of Florida, Gainesville, FL, USA.
  • Daniel J Paredes
    University of Florida, Gainesville, FL, USA.
  • Zehao Yu
    Department of Health Outcomes and Biomedical Informatics.
  • Robert J Lucero
    University of California Los Angeles, Los Angeles, CA, USA.

Keywords

External Resources

Popular Topics
Recent Journals