Semi-automated title-abstract screening using natural language processing and machine learning.

Journal: Systematic reviews
PMID: 39487499

Abstract

BACKGROUND: Title-abstract screening in the preparation of a systematic review is a time-consuming task. Modern techniques of natural language processing and machine learning might allow partly automatization of title-abstract screening. In particular, clear guidance on how to proceed with these techniques in practice is of high relevance.

Authors

  • Maximilian Pilz
    Institute of Medical Biometry and Informatics, University of Heidelberg, Heidelberg, Germany.
  • Samuel Zimmermann
    University of Heidelberg - Institute of Medical Biometry, Heidelberg, Germany.
  • Juliane Friedrichs
    Medical Faculty of the Martin Luther University Halle-Wittenberg - Department of Visceral, Vascular and Endocrine Surgery, Halle (Saale), Germany.
  • Enrica Wördehoff
    Medical Faculty of the Martin Luther University Halle-Wittenberg - Department of Visceral, Vascular and Endocrine Surgery, Halle (Saale), Germany.
  • Ulrich Ronellenfitsch
    Medical Faculty of the Martin Luther University Halle-Wittenberg - Department of Visceral, Vascular and Endocrine Surgery, Halle (Saale), Germany.
  • Meinhard Kieser
    University of Heidelberg - Institute of Medical Biometry, Heidelberg, Germany.
  • Johannes A Vey
    University of Heidelberg - Institute of Medical Biometry, Heidelberg, Germany.

Keywords

External Resources

Popular Topics
Recent Journals