Clinical Research Directory

Theory-Guided Socratic AI Scaffolding for Clinical Reasoning in Nursing Students

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.

MAGICS - Multi-Agent Generative AI in Clinical Simulation for Clinical Deterioration Training

This study compares the effectiveness of a Generative AI-integrated blended simulation programme and high-fidelity simulation alone on nursing students' clinical reasoning and learning experience during deterioration training

Comparative Case Learning in Undergraduate Nursing Students

This randomized controlled educational trial compares two ways of teaching undergraduate nursing students to reason through clinical cases. Both study arms receive the same eight training cases, the same total instructional time, and the same individualized feedback on their answers. Students in the comparative-case arm study the training cases in matched pairs and explicitly write both the finding that changes the recommended first action and the general principle it illustrates. Students in the individual-case arm reason through and justify each training case on its own, with the same content and time. Four baseline cases are completed before training, and eight new transfer cases are completed seven days after training (acceptance window Day 5-9). The single primary outcome is a 0-100 reasoned clinical decision transfer score at Day 7, derived from two independent, blinded raters. The trial targets 360 randomized nursing students (Years 1-4) at a single site, and the primary analysis will estimate the between-group difference in transfer score adjusted for baseline performance, class year, and session block. The study evaluates whether making the decision-relevant contrast between paired cases explicit improves near transfer of clinical reasoning under matched content and time; it does not involve real patients or clinical interventions, and it does not produce direct conclusions about real-world patient safety or general clinical competence.