Beyond the Prompt: Leveraging Generative AI and Tanner's Model to Decode Clinical Logic in Undergraduate Nursing

Area of Science:

• Nursing Education
• Artificial Intelligence in Healthcare
• Clinical Judgment Development

Background:

• Undergraduate nursing programs face challenges in transitioning students from theory to clinical practice.
• Traditional teaching methods often fail to provide the iterative practice necessary to achieve practice readiness.
• A significant gap exists between theoretical knowledge and the demands of clinical nursing environments.

Purpose of the Study:

• To describe an innovative pedagogical approach integrating Generative Artificial Intelligence (GenAI) with Tanner's Clinical Judgment Model.
• To develop nonlinear, algorithmic thinking patterns in nursing students.
• To enhance clinical reasoning skills through AI-assisted learning.

Main Methods:

• Utilizing an "If This, Then That" logic framework for GenAI integration.
• Employing GenAI as a "thinking partner" to construct clinical logic.
• Structuring the learning process around Tanner's 4 phases: Noticing, Interpreting, Responding, and Reflecting.

Main Results:

• AI-augmented iterative algorithms shift focus from rote memorization to spatial-logical mapping.
• The approach promotes metacognition and enhances complex pattern recognition abilities.
• Students transition from linear thinking to more sophisticated clinical problem-solving.

Conclusions:

• GenAI, when used as a scaffolded, iterative tool, significantly enhances clinical synthesis.
• This pedagogical strategy better prepares nursing students for the complexities of real-world clinical practice.
• The integration of GenAI supports the development of critical thinking and clinical judgment in novice nurses.