An AI Educational Agent for Medical Machine Learning Courses
Trial statusRecruiting
Trial phaseNot applicable
Trial typeInterventional
Biological sexAll
AgeNot listed
SponsorSun Yat-sen University
About this trial
The goal of this interventional study is to evaluate the effectiveness of a Large Language Model (LLM)-based educational AI Agent in graduate students (Masters and PhD) specializing in medicine or nursing who are enrolled in the "Machine Learning and Data Mining" course. The main questions it aims to answer are:
Does the use of an educational AI Agent improve students' academic performance and practical skills in machine learning compared to traditional methods?
Does the AI intervention enhance students' learning confidence, satisfaction, and cognitive engagement?
Researchers will compare students currently using the AI Agent (experimental group) to a historical control group (students from the previous cohort who did not use the AI tool) to see if the AI-assisted learning model leads to significantly higher learning achievements and better educational experiences.
Participants will:
Utilize the Teaching Agent for real-time answers to theoretical questions, personalized study planning, and knowledge reinforcement.
Engage with the Research Agent to assist with literature reviews, research design optimization, and academic writing structure.
Use the Practice Innovation Agent for guidance on coding, algorithm debugging, and applying machine learning models to medical data analysis projects.
Eligibility criteria
This trial accepts healthy volunteersQualifiers
Medical graduate students from universities in the Guangdong-Hong Kong-Macao Greater Bay Area;
Graduate students who have taken the "Machine Learning and Data Mining" course;
Have completed the required prerequisite courses: "Medical Statistics" and "Nursing Research";
Capable of operating the AI Educational Agent system normally and willing to undergo relevant teaching interventions and assessments during the study period.
Disqualifiers
Unwilling to use the AI education agent system, or refusing to allow the research team to collect their relevant data;
Students who cannot commit to the full duration of the course or have known scheduling conflicts that would prevent regular attendance;
Students who have previously enrolled in or audited this course in prior academic years to avoid learning effect bias
Trial design
Design model
Single group
Treatments tested in this trial
KGRAG-based AI Educational Agent System
Other interventionThe intervention involves a custom-developed AI educational system powered by Large Language Models (LLMs) and Knowledge Graph-based Retrieval-Augmented Generation (KGRAG) technology. The system comprises three specialized agents to support self-directed learning: 1. Teaching Agent: Provides real-time concept explanations, personalized study plans, and knowledge reinforcement based on the course curriculum. 2. Research Agent: Assists with literature review, research question refinement, and academic writing structure. 3. Practice Innovation Agent: Guides students through code generation, algorithm debugging, and data mining projects using Socratic tutoring methods to foster problem-solving skills. Participants have 24/7 access to this system throughout the semester.
Treatment groups
56 Participants
are divided into 1 treatment groupGroup A: AI Agent Intervention GroupExperimental treatment 1 intervention
Trial outcomes
Primary outcomes
1
Composite Academic Performance Score
Assessed through the final cumulative course grade (range: 0-100), which indicates the student's overall mastery of machine learning concepts and applications. The score is calculated based on three weighted components: In-class Assignments (20%): Evaluations of regular assignments submitted via the course platform. Research Progress Paper (40%): A written paper on a free-exploration topic assessing theoretical understanding and research design skills. Group Final Project Presentation (40%): Assessment of a practical project where students present solutions and results based on given medical cases and datasets. Higher scores indicate better academic performance. The experimental group's scores will be compared with the historical control group
Time frame
After the intervention (at the end of the course, approximately week 3)Secondary outcomes
1
Objective Knowledge Acquisition Rate
Evaluated using a structured knowledge assessment embedded in the course surveys. The assessment includes multiple-choice questions covering core concepts , data processing methods , and ethical considerations. The outcome is reported as the percentage of correct responses
Time frame
After the intervention (at the end of the course, approximately week 3)2
Perceived Usefulness and Technology Acceptance
Assessed using the post-course survey based on the Technology Acceptance Model (TAM). Participants rate the helpfulness of the AI Agent for their research and work on a scale of 0 (No help) to 10 (Very helpful)
Time frame
After the intervention (at the end of the course, approximately week 3)3
AI Agent Engagement: Interaction Frequency
Total number of conversations and conversational turns per student, assessed via quantitative analysis of backend system logs to measure student engagement behavior.
Time frame
At the end of the course (approximately Week 3)4
AI Agent Engagement: Temporal Patterns
Comparison of AI agent usage frequency during exam preparation weeks versus regular study weeks, assessed via quantitative analysis of backend system logs.
Time frame
At the end of the course (approximately Week 3)Sponsors and contacts
Click on the lead sponsor to view all of their trials.
Source ClinicalTrials.gov