Topic evolution before fall incidents in new fallers through natural language processing of general practitioners' clinical notes.

Journal: Age and ageing
Published Date: Feb 1, 2024

Abstract

BACKGROUND: Falls involve dynamic risk factors that change over time, but most studies on fall-risk factors are cross-sectional and do not capture this temporal aspect. The longitudinal clinical notes within electronic health records (EHR) provide an opportunity to analyse fall risk factor trajectories through Natural Language Processing techniques, specifically dynamic topic modelling (DTM). This study aims to uncover fall-related topics for new fallers and track their evolving trends leading up to falls.

Authors

  • Noman Dormosh
    Department of Medical Informatics, Amsterdam UMC location University of Amsterdam, Amsterdam, The Netherlands.
  • Ameen Abu-Hanna
    Department of Medical Informatics, Amsterdam Public Health Research Institute, Amsterdam UMC, University of Amsterdam, Meibergdreef 9, 1105AZ, Amsterdam, The Netherlands.
  • Iacer Calixto
    Department of Medical Informatics, Amsterdam UMC location University of Amsterdam, Amsterdam, The Netherlands.
  • Martijn C Schut
    Department of Medical Informatics, Amsterdam UMC (location AMC), Amsterdam, The Netherlands.
  • Martijn W Heymans
    Department of Epidemiology and Data Science, Amsterdam UMC location Vrije Universiteit Amsterdam, Amsterdam, The Netherlands.
  • Nathalie van der Velde
    Department of Internal Medicine, Section of Geriatric Medicine, Amsterdam UMC location University of Amsterdam, Amsterdam, The Netherlands.

Keywords

External Resources

Popular Topics
Recent Journals