Utilizing Large language models to select literature for meta-analysis shows workload reduction while maintaining a similar recall level as manual curation.

Journal: BMC medical research methodology
PMID: 40295957

Abstract

BACKGROUND: Large language models (LLMs) like ChatGPT showed great potential in aiding medical research. A heavy workload in filtering records is needed during the research process of evidence-based medicine, especially meta-analysis. However, few studies tried to use LLMs to help screen records in meta-analysis.

Authors

  • Xiangming Cai
    Department of Molecular Cell Biology & Immunology, Amsterdam Infection & Immunity Institute and Cancer Center Amsterdam, Amsterdam UMC, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands. x.cai@amsterdamumc.nl.
  • Yuanming Geng
    Department of Neurosurgery, Jinling Hospital, Nanjing, China.
  • Yiming Du
    Department of System Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong, China.
  • Bart Westerman
    Department of Neurosurgery, Cancer Center Amsterdam, Brain Tumor Center Amsterdam, Amsterdam UMC Location Vrije Universiteit Amsterdam, Amsterdam, The Netherlands.
  • Duolao Wang
    Department of Clinical Sciences, Liverpool School of Tropical Medicine, Liverpool, UK. duolao.wang@lstmed.ac.uk.
  • Chiyuan Ma
    Department of Neurosurgery, Jinling Hospital, Nanjing, China. machiyuan_nju@126.com.
  • Juan J Garcia Vallejo
    Department of Molecular Cell Biology & Immunology, Amsterdam Infection & Immunity Institute and Cancer Center Amsterdam, Amsterdam UMC, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands.

Keywords

External Resources

Popular Topics
Recent Journals