Back

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

Cai, X.; Geng, Y.; Du, Y.; Westerman, B.; Wang, D.; Ma, C.; Vallejo, J. J. G.

2023-09-07 epidemiology
10.1101/2023.09.06.23295072 medRxiv
Show abstract

BackgroundLarge 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, no study tried to use LLMs to help screen records in meta-analysis. ObjectiveIn this research, we aimed to explore the possibility of incorporating ChatGPT to facilitate the screening step based on the title and abstract of records during meta-analysis. MethodsTo 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. ResultsA variable performance was found between different single-prompts with a mean recall of 0.841. Based on these single-prompts, we were able to find combinations with performance better than the pre-set threshold. Finally, with a best combination of criteria identified, LARS-GPT showed a 39.5% workload reduction on average with a recall greater than 0.9. ConclusionsWe show here the groundbreaking finding that automatic selection of literature for meta-analysis is possible with ChatGPT. We provide it here as a pipeline, LARS-GPT, which showed a great workload reduction while maintaining a pre-set recall.

Matching journals

The top 14 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.