JMIR Publications

ABSTRACT

Background:

Rapidly and accurately synthesizing large volumes of evidence is a time and resource-intensive process. Once published, reviews often risk becoming outdated, limiting their usefulness for decision-makers. Recent advancements in artificial intelligence (AI) have enabled researchers to automate various stages of the evidence synthesis process, from literature searching and screening to data extraction.

Objective:

We aimed to map the current landscape of AI tools used to automate evidence synthesis.

Methods:

Following the JBI methodology for scoping reviews, we searched Ovid MEDLINE, Ovid Embase, Scopus, and Web of Science in February 2025, and conducted a grey literature search in April 2025. We included articles published in any language from January 2021 onwards. Two reviewers independently screened citations using Rayyan, and we extracted data based on study design and key AI-related technical features.

Results:

We identified 7,841 unique citations through database searches and 19 additional records through a grey literature search. A total of 222 articles were included in the review. We identified 65 AI tools that automate either specific tasks or the entire evidence synthesis process. More than half of the included studies were published in 2024, reflecting a trend in the use of general-purpose large language models (LLMs) for evidence synthesis. Title and abstract screening, as well as data extraction, were the most studied tasks for automation.

Conclusions:

A broad, evolving suite of AI tools is available to support automation in evidence synthesis, leveraged by increasingly complex AI methods. Optimal tool selection likely will depend on the review topic, researcher priorities, and specific tasks. While these tools offer potential for reducing manual workload, ongoing evaluation to mitigate AI bias, and ensure quality and integrity of reviews, is essential for safeguarding evidence-based decision-making.