Large language models for conducting systematic reviews: on the rise, but not yet ready for use - a scoping review

Background

Machine learning (ML) promises versatile help in the creation of systematic reviews (SRs). Recently, further developments in the form of large language models (LLMs) and their application in SR conduct attracted attention.

Objective

To provide an overview of ML and specifically LLM applications in SR conduct in health research.

Study design

We systematically searched MEDLINE, Web of Science, IEEEXplore, ACM Digital Library, Europe PMC (preprints), Google Scholar, and conducted an additional hand search (last search: 26 February 2024). We included scientific articles in English or German, published from April 2021 onwards, building upon the results of a mapping review with a related research question. Two reviewers independently screened studies for eligibility; after piloting, one reviewer extracted data, checked by another.

Results

Our database search yielded 8054 hits, and we identified 33 articles from our hand search. Of the 196 included reports, 159 described more traditional ML techniques, 37 focused on LLMs. LLM approaches covered 10 of 13 defined SR steps, most frequently literature search (n=15, 41%), study selection (n=14, 38%), and data extraction (n=11, 30%). The mostly recurring LLM was GPT (n=33, 89%). Validation studies were predominant (n=21, 57%). In half of the studies, authors evaluated LLM use as promising (n=20, 54%), one quarter as neutral (n=9, 24%) and one fifth as non-promising (n=8, 22%).

Conclusions

Although LLMs show promise in supporting SR creation, fully established or validated applications are often lacking. The rapid increase in research on LLMs for evidence synthesis production highlights their growing relevance.

HIGHLIGHTS