The goal of this study was to compare two approaches to using generative artificial intelligence (AI) to support clinical reasoning in undergraduate nursing students. The study examined whether a theory-guided Socratic AI scaffold based on Tanner's Clinical Judgment Model could better support clinical reasoning, case-based knowledge, and confidence than the naturalistic use of general-purpose generative AI. Participants were undergraduate nursing students enrolled in a pediatric nursing course. Before the intervention, students' perceived barriers to clinical reasoning were identified and used to inform the theory-guided AI scaffold. Classes were then assigned to either Tanner-Structured Socratic AI Scaffolding or General-Purpose Generative AI. Both groups worked with the same pediatric fever case for the same amount of time. Students in the Tanner-Structured Socratic AI Scaffolding group received step-by-step guidance through Noticing, Interpreting, Responding, and Reflecting using Socratic questions, hints, feedback, and prompts for reflection. Students in the General-Purpose Generative AI group used freely available generative AI tools as they normally would for learning. The study compared the two groups on clinical reasoning performance, case-based knowledge, and confidence in clinical reasoning.
Study Type
INTERVENTIONAL
Allocation
RANDOMIZED
Purpose
OTHER
Masking
DOUBLE
Enrollment
127
Participants used a research-team-developed AI chatbot structured around Tanner's Clinical Judgment Model. The chatbot guided participants sequentially through Noticing, Interpreting, Responding, and Reflecting using Socratic questions, graduated hints, metacognitive prompts, and constructive feedback rather than providing direct answers. The scaffolding was informed by learner-identified barriers to clinical reasoning.
Participants used freely accessible general-purpose generative AI tools as they normally would for learning. They formulated their own task-focused queries and received no Tanner-structured sequence or standardized Socratic prompts.
Chang Gung University of Science and Technology
Taoyuan, Taiwan
Clinical Reasoning Performance
Clinical reasoning performance was assessed using the Clinical Reasoning Performance Rubric (CRPR), a 15-point criterion-referenced rubric. Participants identified three priority nursing problems, ranked them by urgency, and proposed three evidence-based interventions for each problem. Total scores ranged from 0 to 15, with higher scores indicating better clinical reasoning performance.
Time frame: Immediately after the intervention
Case-Based Knowledge
A five-item, scenario-based, single-best-answer test assessed infant fever management across assessment, problem identification, goal setting, intervention, and evaluation.
Time frame: Baseline and immediately after the intervention
Clinical Reasoning Confidence
Self-reported confidence in clinical reasoning and decision-making for the pediatric fever case was assessed with a single 5-point item ranging from 1 (very low confidence) to 5 (very high confidence).
Time frame: Baseline and immediately after the intervention
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.