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

October 20, 2026 updated by: Ying-Mei Liu, Chang Gung University of Science and Technology

Effects of Integrating a Reasoning Grid and ChatGPT on 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.

Study Overview

Status

Completed

Conditions

Intervention / Treatment

Study Type

Interventional

Enrollment (Actual)

127

Phase

  • Not Applicable

Contacts and Locations

This section provides the contact details for those conducting the study, and information on where this study is being conducted.

Study Locations

      • Taoyuan, Taiwan
        • Chang Gung University of Science and Technology

Participation Criteria

Researchers look for people who fit a certain description, called eligibility criteria. Some examples of these criteria are a person's general health condition or prior treatments.

Eligibility Criteria

Ages Eligible for Study

  • Child
  • Adult
  • Older Adult

Accepts Healthy Volunteers

Yes

Genders Eligible for Study

All

Description

Inclusion Criteria:

  • Undergraduate nursing students enrolled in the required Pediatric Nursing course.
  • Completion of core medical-surgical nursing courses.
  • No prior practicum experience in specialized pediatric units.

Exclusion Criteria:

  • Students repeating the Pediatric Nursing course.
  • Students with prior pediatric specialty rotation experience.

Study Plan

This section provides details of the study plan, including how the study is designed and what the study is measuring.

How is the study designed?

Design Details

  • Primary Purpose: Other
  • Allocation: Randomized
  • Interventional Model: Parallel Assignment
  • Masking: Double

Arms and Interventions

Participant Group / Arm
Intervention / Treatment
Experimental: Tanner-Structured Socratic AI Scaffolding

Participants used a theory-guided AI chatbot structured around Tanner's Clinical Judgment Model. The chatbot guided participants through Noticing, Interpreting, Responding, and Reflecting using Socratic questions, graduated hints, metacognitive prompts, and constructive feedback rather than providing direct answers.

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.

Active Comparator: General-Purpose Generative AI

Participants used freely accessible general-purpose generative AI tools as they normally would for learning. They formulated their own task-focused queries without a Tanner-structured sequence or standardized Socratic prompts.

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.

What is the study measuring?

Primary Outcome Measures

Outcome Measure
Measure Description
Time Frame
Clinical Reasoning Performance
Time Frame: Immediately after the intervention

Clinical reasoning performance was assessed using the Clinical Reasoning Performance Rubric (CRPR), a 15-point criterion-referenced rubric. Participants identified three priority nursing problems (0-3 points), ranked them in order of urgency (0-3 points), and proposed three appropriate nursing interventions for each problem (0-9 points). Total scores ranged from 0 to 15, with higher scores indicating better clinical reasoning performance.

Immediately after the intervention

Secondary Outcome Measures

Outcome Measure
Measure Description
Time Frame
Case-Based Knowledge
Time Frame: Baseline and immediately after the intervention

Case-based knowledge was assessed using a five-item, scenario-based, single-best-answer knowledge test covering infant fever management across five domains: assessment, problem identification, goal setting, intervention, and evaluation. Each correct answer was awarded 1 point, and incorrect answers received 0 points. Total scores ranged from 0 to 5, with higher scores indicating greater case-based knowledge.

Baseline and immediately after the intervention
Clinical Reasoning Confidence
Time Frame: Baseline and immediately after the intervention

Clinical reasoning confidence was assessed using a single-item, self-reported 5-point rating scale measuring participants' confidence in clinical reasoning and decision-making related to a pediatric fever case. Scores ranged from 1 (very low confidence) to 5 (very high confidence), with higher scores indicating greater clinical reasoning confidence.

Baseline and immediately after the intervention

Collaborators and Investigators

This is where you will find people and organizations involved with this study.

Sponsor

Study record dates

These dates track the progress of study record and summary results submissions to ClinicalTrials.gov. Study records and reported results are reviewed by the National Library of Medicine (NLM) to make sure they meet specific quality control standards before being posted on the public website.

Study Major Dates

Study Start (Actual)

September 15, 2025

Primary Completion (Actual)

February 5, 2026

Study Completion (Actual)

February 5, 2026

Study Registration Dates

First Submitted

September 18, 2026

First Submitted That Met QC Criteria

September 18, 2026

First Posted (Actual)

September 24, 2026

Study Record Updates

Last Update Posted (Actual)

October 22, 2026

Last Update Submitted That Met QC Criteria

October 20, 2026

Last Verified

October 1, 2026

More Information

Terms related to this study

Other Study ID Numbers

  • 202401895B0

Plan for Individual participant data (IPD)

Plan to Share Individual Participant Data (IPD)?

NO

Drug and device information, study documents

Studies a U.S. FDA-regulated drug product

No

Studies a U.S. FDA-regulated device product

No

This information was retrieved directly from the website clinicaltrials.gov without any changes. If you have any requests to change, remove or update your study details, please contact register@clinicaltrials.gov. As soon as a change is implemented on clinicaltrials.gov, this will be updated automatically on our website as well.