Aligning text mining and machine learning algorithms with best practices for study selection in systematic literature reviews.

Journal: Systematic reviews
Published Date:

Abstract

BACKGROUND: Despite existing research on text mining and machine learning for title and abstract screening, the role of machine learning within systematic literature reviews (SLRs) for health technology assessment (HTA) remains unclear given lack of extensive testing and of guidance from HTA agencies. We sought to address two knowledge gaps: to extend ML algorithms to provide a reason for exclusion-to align with current practices-and to determine optimal parameter settings for feature-set generation and ML algorithms.

Authors

  • E Popoff
    Precision HEOR, 1505 West 2nd Ave #300, Vancouver, British Columbia, V6H3Y4, Canada.
  • M Besada
    Precision HEOR, 1505 West 2nd Ave #300, Vancouver, British Columbia, V6H3Y4, Canada. mariam.besada@precisionvh.com.
  • J P Jansen
    Precision HEOR, Oakland, CA, USA.
  • S Cope
    Precision HEOR, 1505 West 2nd Ave #300, Vancouver, British Columbia, V6H3Y4, Canada.
  • S Kanters
    Precision HEOR, 1505 West 2nd Ave #300, Vancouver, British Columbia, V6H3Y4, Canada.