Systematic Reviews: AI in Systematic Reviews

Readers planning or supervising a systematic review can use this guide to decide which stages AI tools may support, such as calibrated title and abstract screening, deduplication, and human-verified data extraction, and which must stay fully human, including searching, inclusion and exclusion decisions, risk-of-bias appraisal, synthesis, and unverified manuscript text. Before adopting any tool, they can work through the page's evaluation questions on validation, transparency, exportable audit trails, and institutional compliance, and they can follow its PRISMA 2020-based list of what a manuscript must report about automation, from which tool was used to the level of human oversight. The page also routes readers to the RAISE recommendations, Cochrane guidance, and a further-reading list for going deeper into responsible AI use in evidence synthesis.

Task

Research & literature

Time

10 minutes

Level

intermediate

Cost

Free — Nothing to pay. A free account at most.

Tools

None in particular

Published

2026-09-15