ChatGPT Helping Advance Training for Medical Students: A Study on Self-Directed Learning Enhancement (CHAT-MS)

Enhancement of Self-Directed Learning Through Custom GPT's AI Facilitation Among Medical Students: A Open-label, Randomized Controlled Trial

The goal of this clinical trial is to evaluate the effect of LearnGuide, a custom GPT developed with ChatGPT for supporting self-directed learning (SDL) in medical students. The main questions it aims to answer are:

How does LearnGuide influence SDL skills among medical students? Can LearnGuide improve critical thinking and learning flow as measured by Cornell Critical Thinking Test (CCTT) Level Z score and Global Flow Score (GFS)?

Participants will:

Undergo a two-hour introduction to LearnGuide. Engage in 12 weeks of SDL task-based training with LearnGuide's support.

If there is a comparison group: Researchers will compare the group utilizing LearnGuide for SDL and the group without this tool to see if there is a significant difference in SDL skills, critical thinking, and learning flow experiences.

Study Overview

• Status: Completed
• Conditions: Medical Education; Artificial Intelligence; Self-Directed Learning
• Intervention / Treatment: Other: custom GPT supported self-directed learning

• Study Type: Interventional
• Enrollment (Actual): 103
• Phase: Not Applicable

Contacts and Locations

Study Locations

• China
  • Hunan
    • Changsha, Hunan, China, 410011
      • Department of Geriatirc Surgery

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child; Adult; Older Adult
• Accepts Healthy Volunteers: Yes

Description

Inclusion Criteria:

• Undergraduate and postgraduate students studying at the Second Xiangya Hospital
• with access to ChatGPT

Exclusion Criteria:

• utilization of large language models for learning assistance more than once weekly for a period exceeding 2 months.

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Other
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: None (Open Label)

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: Intervention group; Engage in 12 weeks of SDL task-based training with LearnGuide's support.	Other: custom GPT supported self-directed learning; The intervention in our study involved a LearnGuide utilization guide course along with a 12-week integrated training program that incorporated LearnGuide. In the first two-hour session, instructional staff introduced LearnGuide through a hands-on demonstration, teaching students how to use ChatGPT effectively by crafting high-quality prompts. The team emphasized LearnGuide's role as an "AI facilitator" in self-directed learning (SDL). Following the introduction, students were assigned various tasks including online learning, literature reviews, case analyses, and Problem-Based Learning (PBL) activities. Over the 12-week SDL phase with LearnGuide, students were required to complete at least one of these tasks weekly. This setup allowed students to consult mentors for any LearnGuide-related questions, enhancing their learning experience.
No Intervention: control group; the control group engaged in SDL task-based training without the support of LearnGuide or any similar artificial intelligence (AI) assistance.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Self-Directed Learning Scale	Utilizing a five-point Likert scale across ten items, assesses learning autonomy in adolescents and adults. Anchored in Brockett's framework, it quantifies learners' independent learning inclination, exhibiting robust internal consistency and validity	at 6 ，12 and 14 weeks

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Cornell Critical Thinking Test (CCTT) Level Z	The CCTT Level Z measures cognitive abilities in students beyond 11th grade with 52 multiple-choice questions across six domains based on the Ennis and Millman Theory, including deductive and inductive reasoning, semantic analysis, credibility assessment, experimental planning, and assumption identification	at 6 ，12 and 14 weeks
Flow Short Scale	The Flow Short Scale (FSS), a condensed form of the Flow State Scale, features ten items on a 7-point scale to assess the flow experience across various activities, from sports to gaming. Its concise yet comprehensive format has made it widely used for evaluating flow experiences in diverse settings	at 6 and 12 weeks

Collaborators and Investigators

• Sponsor: Wang Shalong
• Collaborators: Central South University

Study record dates

Study Major Dates

• Study Start (Actual): November 25, 2023
• Primary Completion (Actual): March 18, 2024
• Study Completion (Actual): April 15, 2024

Study Registration Dates

• First Submitted: February 17, 2024
• First Submitted That Met QC Criteria: February 17, 2024
• First Posted (Actual): February 23, 2024

Study Record Updates

• Last Update Posted (Actual): May 16, 2024
• Last Update Submitted That Met QC Criteria: May 14, 2024
• Last Verified: May 1, 2024

More Information

Terms related to this study

• Keywords: Artificial Intelligence; Medical Education; self-directed learning; ChatGPT; large language model
• Other Study ID Numbers: DGETRRP2023-54

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: UNDECIDED
• IPD Plan Description: In our study, the decision regarding the sharing of individual participant data (IPD) has not yet been made due to ongoing considerations about privacy, consent, and data protection. We are currently evaluating the ethical implications and ensuring compliance with relevant data protection regulations before making a decision. Additionally, we aim to assess the feasibility of anonymizing IPD in a manner that maintains the integrity and utility of the data for potential future research. Our priority is to safeguard participant confidentiality and respect their consent preferences, while also considering the value of data sharing for advancing scientific knowledge. Further discussions and consultations with stakeholders are planned to reach a well-informed decision.

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No