Machine learning to optimize literature screening in medical guideline development.

Journal: Systematic reviews
PMID: 38992684

Abstract

OBJECTIVES: In a time of exponential growth of new evidence supporting clinical decision-making, combined with a labor-intensive process of selecting this evidence, methods are needed to speed up current processes to keep medical guidelines up-to-date. This study evaluated the performance and feasibility of active learning to support the selection of relevant publications within medical guideline development and to study the role of noisy labels.

Authors

  • Wouter Harmsen
    Knowlegde Institute for the Federation of Medical Specialists, Utrecht, The Netherlands.
  • Janke de Groot
    Knowlegde Institute for the Federation of Medical Specialists, Utrecht, The Netherlands.
  • Albert Harkema
    Department of Methodology and Statistics, Faculty of Social and Behavioral Sciences, Utrecht University, Utrecht, The Netherlands.
  • Ingeborg van Dusseldorp
    Knowlegde Institute for the Federation of Medical Specialists, Utrecht, The Netherlands.
  • Jonathan de Bruin
    Department of Research and Data Management Services, Information Technology Services, Utrecht University, Utrecht, The Netherlands.
  • Sofie van den Brand
    Department of Methodology and Statistics, Faculty of Social and Behavioral Sciences, Utrecht University, Utrecht, The Netherlands.
  • Rens van de Schoot
    Department of Methodology and Statistics, Faculty of Social and Behavioral Sciences, Utrecht University, Utrecht, Netherlands.

Keywords

External Resources

Popular Topics
Recent Journals