Pedagogical strategies for enhancing critical thinking in nursing students using large language models: a mixed-methods systematic review protocol.

Clinical Snapshot

Key Findings

• P Value: Not applicable at protocol stage

• Effect Size: Not applicable — protocol stage; quantitative synthesis planned via SWiM (no pooled effect size will be generated)

• Primary Outcome: Protocol only — no results available. Planned primary outcome: critical thinking competency in undergraduate nursing students, classified using a modified Kirkpatrick framework

• Nnt Or Sensitivity: Not applicable — educational intervention review; no NNT calculable. Direction-of-effect tables via SWiM are the planned analogue for effect estimation

• Confidence Interval: Not applicable at protocol stage

Clinical Application

Feasibility of the planned review is moderate-to-high given the clear JBI methodology, multi-database search, and experienced authorship team. However, the primary study base in this field is nascent and likely small, which may limit the depth of synthesis achievable. The planned dissemination via a visual guide for educators is a practical and accessible knowledge translation strategy. Directly relevant to Australian nursing education. The Australian Nursing and Midwifery Accreditation Council (ANMAC) standards require demonstration of critical thinking as a graduate attribute. The Nursing and Midwifery Board of Australia (NMBA) Registered Nurse Standards for Practice explicitly mandate critical thinking and analysis (Standard 1). Australian universities are actively integrating generative AI tools into health professional education, and RACGP and AHPRA have issued guidance on AI literacy in clinical training. The University of the Sunshine Coast co-authorship ensures Australian contextual awareness. Findings will be relevant to curriculum designers, nursing school directors, and clinical educators across Australian universities navigating TGA and AHPRA expectations for AI-competent graduates. No PBS or TGA regulatory implications apply directly to this educational intervention review. Undergraduate nursing students in tertiary education settings where LLM-based tools are integrated into curricula. Findings, when available, will be most directly applicable to pre-registration nursing programmes in English-speaking countries with comparable regulatory frameworks (Australia, New Zealand, United Kingdom, Canada).

Abstract

INTRODUCTION: Large language models (LLMs) are rapidly normalising in nursing education. However, evidence regarding their impact on critical thinking-a cornerstone of safe clinical practice-remains inconsistent. Current syntheses have largely focused on student satisfaction and general utility, leaving the specific instructional mechanisms that cultivate this competency unexplored. This mixed-methods systematic review aims to identify effective pedagogical strategies for fostering critical thinking, providing evidence-based guidance to safeguard clinical competency in an artificial intelligence-integrated workforce. METHODS AND ANALYSIS: This review will follow a convergent segregated mixed-methods design in accordance with the Joanna Briggs Institute (JBI) methodology. A systematic search will be conducted across CINAHL, ERIC, MEDLINE, PsycINFO and Scopus supplemented by grey literature sources (ProQuest Dissertations, MedRxiv). The search will be limited to English-language studies published from January 2023 to June 2026. Eligible studies will include undergraduate nursing students exposed to structured LLM-based pedagogical interventions. Methodological quality will be appraised using design-specific JBI Critical Appraisal Checklists. Outcomes will be classified using a modified Kirkpatrick framework to distinguish objective competence from subjective confidence. Quantitative data will be synthesised narratively following Synthesis Without Meta-analysis guidelines, and qualitative data thematically. Streams will be integrated using a Joint Display Analysis to generate meta-inferences on effective instructional design. Finally, confidence in the cumulative evidence will be assessed using Grading of Recommendations Assessment, Development and Evaluation (GRADE) and GRADE-Confidence in the Evidence from Reviews of Qualitative research. ETHICS AND DISSEMINATION: As a systematic review of existing literature, this study does not require ethical approval. Findings will be disseminated through a peer-reviewed publication, conference presentations and a visual guide for educators.

References

1. 1.Oh, L., Mearns, G., & Mowat, R. (2026). Pedagogical strategies for enhancing critical thinking in nursing students using large language models: a mixed-methods systematic review protocol. BMJ Open. https://doi.org/10.1136/bmjopen-2026-119386