Crystallizing Theory Evaluation: A Human-AI Collaborative Framework for Multi-Perspective Nursing Theory Analysis

Area of Science:

• Nursing Education Theory
• Simulation Theory
• Meta-theoretical Analysis

Background:

• The NLN/Jeffries Simulation Theory (JST) is widely used but lacks theoretical clarity, leading to assessment challenges.
• Traditional evaluation methods are fragmented, failing to resolve contradictions in JST's application.
• A need exists for comprehensive theoretical analysis to understand JST's role in nursing education.

Purpose of the Study:

• To present a Human-AI collaborative framework for meta-theoretical analysis.
• To use JST as a case study to demonstrate the framework's utility.
• To re-evaluate the theoretical clarity and application of JST in nursing.

Main Methods:

• Developed a Human-AI collaborative framework based on crystallization.
• Integrated evaluation criteria from Fawcett, Meleis, and Walker and Avant.
• Employed AI for systematic analysis of theoretical evidence and human researchers for interpretation.

Main Results:

• JST's perceived lack of precision is a strength, enabling its function as a boundary object.
• The framework facilitated a comprehensive, meta-theoretical analysis of JST.
• AI augmented human interpretation, demonstrating a practical model for academic research.

Conclusions:

• JST serves as a flexible structure promoting collaboration in nursing education, research, and practice.
• Human-AI collaboration offers a transparent and effective model for academic research.
• Technological tools can enhance, not replace, scholarly critical judgment in nursing.