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

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 rec...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiangming Cai, Yuanming Geng, Yiming Du, Bart Westerman, Duolao Wang, Chiyuan Ma, Juan J. Garcia Vallejo
Format: Article
Language:English
Published: BMC 2025-04-01
Series:BMC Medical Research Methodology
Subjects:
Online Access:https://doi.org/10.1186/s12874-025-02569-3
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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. Objective In this research, we aimed to explore the possibility of incorporating multiple LLMs to facilitate the screening step based on the title and abstract of records during meta-analysis. Methods Various LLMs were evaluated, which includes GPT-3.5, GPT-4, Deepseek-R1-Distill, Qwen-2.5, Phi-4, Llama-3.1, Gemma-2 and Claude-2. To assess our strategy, we selected three meta-analyses from the literature, together with a glioma meta-analysis embedded in the study, as additional validation. For the automatic selection of records from curated meta-analyses, a four-step strategy called LARS-GPT was developed, consisting of (1) criteria selection and single-prompt (prompt with one criterion) creation, (2) best combination identification, (3) combined-prompt (prompt with one or more criteria) creation, and (4) request sending and answer summary. Recall, workload reduction, precision, and F1 score were calculated to assess the performance of LARS-GPT. Results A variable performance was found between different single-prompts, with a mean recall of 0.800. Based on these single-prompts, we were able to find combinations with better performance than the pre-set threshold. Finally, with a best combination of criteria identified, LARS-GPT showed a 40.1% workload reduction on average with a recall greater than 0.9. Conclusions We show here the groundbreaking finding that automatic selection of literature for meta-analysis is possible with LLMs. We provide it here as a pipeline, LARS-GPT, which showed a great workload reduction while maintaining a pre-set recall.
ISSN:1471-2288