Large language models (LLMs) like ChatGPT have become widely applied in the field of medical research. In the process of conducting systematic reviews, similar tools can be employed to expedite various steps, including defining clinical questions, literature search, document screening, information extraction, and language refinement, etc, thereby conserving resources and enhancing efficiency. However, when utilizing LLMs, attention should be given to transparent reporting, distinguishing between genuine and false content, and avoiding academic misconduct. This article reviews 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 involved in systematic reviews and meta-analyses.