Improving Systematic Review Updates With Natural Language Processing Through Abstract Component Classification and Selection: Algorithm Development and Validation.

Journal: JMIR medical informatics
PMID: 40146984

Abstract

BACKGROUND: A challenge in updating systematic reviews is the workload in screening the articles. Many screening models using natural language processing technology have been implemented to scrutinize articles based on titles and abstracts. While these approaches show promise, traditional models typically treat abstracts as uniform text. We hypothesize that selective training on specific abstract components could enhance model performance for systematic review screening.

Authors

  • Tatsuki Hasegawa
    Division of Drug Informatics, Keio University Faculty of Pharmacy, Tokyo, Japan.
  • Hayato Kizaki
    Keio University Faculty of Pharmacy, Division of Drug Informatics, Tokyo, Japan.
  • Keisho Ikegami
    Division of Drug Informatics, Keio University Faculty of Pharmacy, Tokyo, Japan.
  • Shungo Imai
    Faculty of Pharmaceutical Sciences, Hokkaido University, Sapporo, Japan.
  • Yuki Yanagisawa
    Division of Drug Informatics, Keio University Faculty of Pharmacy, Tokyo, Japan.
  • Shuntaro Yada
    Graduate School of Science and Technology, Nara Institute of Science and Technology, Ikoma, Nara, Japan.
  • Eiji Aramaki
    Nara Institute of Science and Technology (NAIST), Japan.
  • Satoko Hori
    Keio University Faculty of Pharmacy, Division of Drug Informatics, Tokyo, Japan.

Keywords

External Resources

Popular Topics
Recent Journals