Human-led and artificial intelligence-automated critical appraisal of systematic reviews: Comparative evaluation
Large language models can support aspects of critical appraisal evidence but lack contextual reasoning and methodological insight required for complex judgments. While Claude 3.7 Sonnet aligned most closely with human reviewers, human oversight remains essential. Large language models should serve as adjuncts and not substitutes for evidence-based practice.
Authors
- Lucija Gosak (ORCID: https://orcid.org/0000-0002-8742-6594)
- Gregor Štiglic (ORCID: https://orcid.org/0000-0002-0183-8679)
- Wilson Tam (ORCID: https://orcid.org/0000-0003-0641-3060)
- Dominika Vrbnjak (ORCID: https://orcid.org/0000-0003-4952-078X)
Institutions
- National University of Singapore (SG)
- University of Maribor (SI)
Publication Details
- Journal
- Nurse Education in Practice
- Published
- 2025-10-29
- DOI
- https://doi.org/10.1016/j.nepr.2025.104614
- Citations
- 1
- Primary Topic
- Meta-analysis and systematic reviews
- Type
- article
- Field-Weighted Citation Impact
- 1.40