Evidence Synthesis Reviews (Systematic, Scoping, etc.)

Researchers are interested in using AI tools for evidence synthesis reviews. Currently there are no authoritative recommendations about which tools to use and how to use them. The resources below provide guidance on the current state of AI tools for evidence synthesis, and guide you through the considerations, benefits and limitations of using these tools. 

Responsible AI in Evidence Synthesis (RAISE) guidelines
There are 3 guidelines on this site. The one most relevant to individuals and teams conducting evidence synthesis reviews is RAISE 3 - Selecting and Using Evidence Synthesis Tools.

Artificial Intelligence Methods Group - a collaboration between the Cochrane Collaboration, Campbell Collaboration, JBI and the Centre for Environmental Evidence. 

Things to keep in mind when selecting or using AI tools for evidence synthesis:

• AI is a companion, not a replacement - these tools work best with human oversight. Most importantly DON'T USE IT for things you don't have an understanding of how to do yourself. If you don't understand it, you can't assess how well the AI tool does it!
• You are ultimately responsible for the outputs of the AI tools you use
• Ensure tools adhere to legal and ethical standards - especially around plagiarism, copyright and intellectual property
• Be wary of tools that may use the data you input to train their models, or that may require you to surrender rights over your own work

Clark J, Barton B, Albarqouni L, Byambasuren O, Jowsey T, Keogh J, et al. Generative artificial intelligence use in evidence synthesis: A systematic review. Res Synth Methods 2025:1–19. https://doi.org/10.1017/rsm.2025.16. 

Gartlehner G, Kugley S, Crotty K, Viswanathan M, Dobrescu A, Nussbaumer-Streit B, et al. AI-Assisted Data Extraction with a Large Language Model: A Study Within Reviews 2025. https://doi.org/10.1101/2025.03.20.25324350.

Lieberum J-L, Toews M, Metzendorf M-I, Heilmeyer F, Siemens W, Haverkamp C, et al. Large language models for conducting systematic reviews: on the rise, but not yet ready for use—a scoping review. Journal of Clinical Epidemiology 2025;181:111746. https://doi.org/10.1016/j.jclinepi.2025.111746.