AI evidence extraction

Using AI to boost scoping reviews : exploring AI deployment in obstetrics and gynaecology as an exemplar

Strathprints: The University of Strathclyde institutional repository (University of Strathclyde) · 2025

AI-generated evidence extraction, verified across multiple analytical personas. Not a substitute for the peer-reviewed original.

9/10

Relevance

0/4

Quality (LMQS)

Evidence

Citations

0.00

FWCI

Methodology & findings

Study design

Comparative scoping review study.

Main result

The study found that "the use of AI tools can enrich and extend the scope of scoping reviews (using a so-called 'Hybrid Review'), but only if the prompts are carefully and thoughtfully crafted." The research demonstrates AI's potential for improving comprehensiveness, time effectiveness, and cost-effectiveness in scoping reviews when applied to obstetrics and gynaecology literature.

Reports effect sizes.

Research paradigm

pragmatist/mixed-methods

Author conclusions

The authors conclude that "the use of AI tools can enrich and extend the scope of scoping reviews (using a so-called 'Hybrid Review'), but only if the prompts are carefully and thoughtfully crafted." This suggests conditional acceptance of AI deployment in systematic literature reviews.

Risk of bias

Selection bias: AI-assisted review may preferentially retrieve or prioritize certain types of literature; Operator bias: Quality of results depends on prompt engineering, which varies by user expertise; Potential publication bias in source databases (MEDLINE); Prompt design bias - outcomes dependent on how prompts are crafted; Potential selection bias in AI tool selection; Limited to single domain (obstetrics and gynaecology) as exemplar

Data: not_statedCode: not_statedExtracted from: pdfAgreement 78%

Explore related topics

Systematic Review Automation Literature Discovery Experimental