Artificial-intelligence tools are being promoted for rapid reviews of scientific literature. A health-focused systematic review organization is testing AI to improve efficiency and scale. Current tools are not ready for broad use, and replacing humans across all methodological tasks is unreliable. Systematic reviews guide clinical care, public-health guidance, and policy decisions, so errors can mislead patients or waste resources. Many AI models mirror human review steps such as study identification, data extraction, and report writing, but systematic reviewing requires specialists to define meaningful questions, assess relevance, interpret findings, and apply clinical or policy context. AI models often lack nuance and can fabricate information, so outputs must be verified by experts. AI support has been evaluated for screening and extraction, which remain time-consuming, especially when data are not easily accessible and must be gathered from multiple sources or inferred from publications.
"Current AI models typically replicate the step-by-step processes by which people conduct systematic reviews: identifying suitable studies from disparate sources; extracting relevant data for analysis; and, finally, writing up the report. The idea is to replace the work of humans. But conducting systematic reviews is not a purely computational task. Human specialists are needed to define meaningful review questions, evaluate relevance, interpret results and understand clinical or policy implications."
"Context and subjective nuance are seldom well-represented in AI models' training data, and the models' tendency to hallucinate that is, to fabricate information means that their outputs need to be verified by human experts. Efforts at Cochrane show the limitations of using AI in place of people. We've been evaluating tools that support study screening and data extraction."
"We are testing ways to use AI to increase our reviews' efficiency and scale. But, in our experience, the current tools are far from ready for mainstream adoption, and the assumption that machines can replace humans on all methodological tasks is flawed. The stakes are high. Systematic reviews and other types of evidence synthesis inform clinical practice, public-health guidance and policy decisions that affect entire populations."
"These are time-consuming processes to conduct manually, particularly when primary data are not readily accessible and must be drawn from multiple sources or inferred from published re"
Read at www.nature.com
Unable to calculate read time
Collection
[
|
...
]