Using natural language processing to extract structured epilepsy data from unstructured clinic letters: development and validation of the ExECT (extraction of epilepsy clinical text) system.

Journal: BMJ open
PMID: 30940752

Abstract

OBJECTIVE: Routinely collected healthcare data are a powerful research resource but often lack detailed disease-specific information that is collected in clinical free text, for example, clinic letters. We aim to use natural language processing techniques to extract detailed clinical information from epilepsy clinic letters to enrich routinely collected data.

Authors

  • Beata Fonferko-Shadrach
    Neurology and Molecular Neuroscience Group, Institute of Life Science, Swansea University Medical School, Swansea University, Swansea, UK.
  • Arron S Lacey
    Neurology and Molecular Neuroscience Group, Institute of Life Science, Swansea University Medical School, Swansea University, Swansea, UK.
  • Angus Roberts
    Department of Computer Science, University of Sheffield, Sheffield, UK.
  • Ashley Akbari
    Health Data Research UK, Data Science Building, Swansea University Medical School, Swansea University, Swansea, UK.
  • Simon Thompson
    Health Data Research UK, Data Science Building, Swansea University Medical School, Swansea University, Swansea, UK.
  • David V Ford
    Health Data Research UK, Data Science Building, Swansea University Medical School, Swansea University, Swansea, UK.
  • Ronan A Lyons
    Health Data Research UK, Data Science Building, Swansea University Medical School, Swansea University, Swansea, UK.
  • Mark I Rees
    Neurology and Molecular Neuroscience Group, Institute of Life Science, Swansea University Medical School, Swansea University, Swansea, UK.
  • William Owen Pickrell
    Neurology and Molecular Neuroscience Group, Institute of Life Science, Swansea University Medical School, Swansea University, Swansea, UK.

Keywords

External Resources

Popular Topics
Recent Journals