Can reproducibility be improved in clinical natural language processing? A study of 7 clinical NLP suites.

Journal: Journal of the American Medical Informatics Association : JAMIA
PMID: 33319904

Abstract

BACKGROUND: The increasing complexity of data streams and computational processes in modern clinical health information systems makes reproducibility challenging. Clinical natural language processing (NLP) pipelines are routinely leveraged for the secondary use of data. Workflow management systems (WMS) have been widely used in bioinformatics to handle the reproducibility bottleneck.

Authors

  • William Digan
    Hôpital Européen Georges Pompidou, AP-HP, Université Paris Descartes, Université Sorbonne Paris Cité, Paris, France.
  • Aurélie Névéol
  • Antoine Neuraz
    Institut National de la Santé et de la Recherche Médicale (INSERM), Centre de Recherche des Cordeliers, UMR 1138 Equipe 22, Paris Descartes, Sorbonne Paris Cité University, Paris, France.
  • Maxime Wack
    INSERM, Centre de Recherche des Cordeliers, UMRS 1138, Université de Paris, Université Sorbonne Paris Cité, Paris, France.
  • David Baudoin
    Centre de Recherche des Cordeliers, INSERM UMRS 1138 Team 22, Université de Paris, Paris, France.
  • Anita Burgun
    Hôpital Necker-Enfants malades, AP-HP, Paris, France.
  • Bastien Rance
    AP-HP, University Hospital Georges Pompidou; INSERM, UMR_S 1138, Centre de Recherche des Cordeliers, Paris, France.

Keywords

External Resources

Popular Topics
Recent Journals