Do it faster with PICOS: Generative AI-Assisted systematic review screening.

Journal: Journal of biomedical informatics
Published Date:

Abstract

BACKGROUND: Systematic reviews (SRs) require substantial time and human resources, especially during the screening phase. Large Language Models (LLMs) have shown the potential to expedite screening. However, their use in generating structured PICOS (Population, Intervention/Exposure, Comparison, Outcome, Study design) summaries from title and abstract to assist human reviewers during screening remains unexplored.

Authors

  • Sai Krishna Vallamchetla
    Department of Neurology, Mayo Clinic, Jacksonville, FL, USA.
  • Omar Abdelkader
    Department of Neurology, Mayo Clinic, Jacksonville, FL, USA.
  • Ali Elnaggar
    Zagazig University, Zagazig, Egypt.
  • Doaa Ramadan
    Department of Neurology, Mayo Clinic, Jacksonville, FL, USA.
  • Md Manjurul Islam Shourav
    Department of Neurology, Mayo Clinic, Jacksonville, FL, USA.
  • Irbaz B Riaz
    Department of Hematology/Oncology, Mayo Clinic, Scottsdale, AZ.
  • Michelle P Lin
    Department of Neurology, Mayo Clinic, Jacksonville, FL, USA. Electronic address: lin.michelle@mayo.edu.