Potential Roles of Large Language Models in the Production of Systematic Reviews and Meta-Analyses

Xufei Luo; Fengxian Chen; Di Zhu; Ling Wang; Zijun Wang; Hui Liu; Meng Lyu; Ye Wang; Qi Wang; Yaolong Chen

doi:10.2196/56780

Potential Roles of Large Language Models in the Production of Systematic Reviews and Meta-Analyses

J Med Internet Res. 2024 Jun 25:26:e56780. doi: 10.2196/56780.

Authors

Xufei Luo^{1

2

3

4

5}, Fengxian Chen⁶, Di Zhu⁷, Ling Wang⁷, Zijun Wang^{1

2

3

4

5}, Hui Liu^{1

2

3

4

5}, Meng Lyu⁷, Ye Wang⁷, Qi Wang^{8

9}, Yaolong Chen^{1

2

3

4

5}

Affiliations

¹ Evidence-Based Medicine Center, School of Basic Medical Sciences, Lanzhou University, Lanzhou, China.
² World Health Organization Collaboration Center for Guideline Implementation and Knowledge Translation, Lanzhou, China.
³ Institute of Health Data Science, Lanzhou University, Lanzhou, China.
⁴ Key Laboratory of Evidence Based Medicine and Knowledge Translation of Gansu Province, Lanzhou University, Lanzhou, China.
⁵ Research Unit of Evidence-Based Evaluation and Guidelines, Chinese Academy of Medical Sciences (2021RU017), School of Basic Medical Sciences, Lanzhou University, Lanzhou, China.
⁶ School of Information Science & Engineering, Lanzhou University, Lanzhou, China.
⁷ School of Public Health, Lanzhou University, Lanzhou, China.
⁸ Department of Health Research Methods, Evidence and Impact, Faculty of Health Sciences, McMaster University, Hamilton, ON, Canada.
⁹ McMaster Health Forum, McMaster University, Hamilton, ON, Canada.

PMID: 38819655
PMCID: PMC11234072
DOI: 10.2196/56780

Abstract

Large language models (LLMs) such as ChatGPT have become widely applied in the field of medical research. In the process of conducting systematic reviews, similar tools can be used to expedite various steps, including defining clinical questions, performing the literature search, document screening, information extraction, and language refinement, thereby conserving resources and enhancing efficiency. However, when using LLMs, attention should be paid to transparent reporting, distinguishing between genuine and false content, and avoiding academic misconduct. In this viewpoint, we highlight the potential roles of LLMs in the creation of systematic reviews and meta-analyses, elucidating their advantages, limitations, and future research directions, aiming to provide insights and guidance for authors planning systematic reviews and meta-analyses.

Keywords: ChatGPT; chatbot; large language model; meta-analysis; systematic review.

©Xufei Luo, Fengxian Chen, Di Zhu, Ling Wang, Zijun Wang, Hui Liu, Meng Lyu, Ye Wang, Qi Wang, Yaolong Chen. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 25.06.2024.

MeSH terms

Humans
Language
Meta-Analysis as Topic*
Review Literature as Topic