This paper is in the following e-collection/theme issue:

Applications of AI (238) Generative Language Models Including ChatGPT (621) New Methods (1096) Research Methodology - AI (26) Reviews on Human Factors (70) Digital Health Reporting Standards, Quality and Transparency in e-Research (118) AI Governance and Policy (9)

Published on in Vol 4 (2025)

Preprints (earlier versions) of this paper are available at https://preprints.jmir.org/preprint/68097, first published .
Critical Assessment of Large Language Models’ (ChatGPT) Performance in Data Extraction for Systematic Reviews: Exploratory Study

Critical Assessment of Large Language Models’ (ChatGPT) Performance in Data Extraction for Systematic Reviews: Exploratory Study

Critical Assessment of Large Language Models’ (ChatGPT) Performance in Data Extraction for Systematic Reviews: Exploratory Study

Authors of this article:

Hesam Mahmoudi1 Author Orcid Image ;   Doris Chang1 Author Orcid Image ;   Hannah Lee1 Author Orcid Image ;   Navid Ghaffarzadegan2 Author Orcid Image ;   Mohammad S Jalali1 Author Orcid Image
Article Authors Cited by Tweetations (1) Metrics

Hesam Mahmoudi   1 , PhD ;   Doris Chang   1 , BSc ;   Hannah Lee   1 , BSc ;   Navid Ghaffarzadegan   2 , PhD ;   Mohammad S Jalali   1 , PhD

1 MGH Institute for Technology Assessment, Harvard Medical School, Boston, MA, United States

2 Industrial and System Engineering Department, Virginia Tech, Falls Church, VA, United States

Corresponding Author:

  • Mohammad S Jalali, PhD
  • MGH Institute for Technology Assessment, Harvard Medical School
  • 125 Nashua St
  • Boston, MA 02114
  • United States
  • Phone: 1 6177243738
  • Email: msjalali@mgh.harvard.edu