Generative AI-Based Evaluation of Clinical Thinking and Decision-Making in Medical Students
Construction of an Intelligent Evaluation System for Clinical Thinking and Decision-making Ability of Medical Students Based on Generative Artificial Intelligence
The goal of this study is to develop and evaluate an intelligent system based on generative artificial intelligence (AI) for assessing clinical thinking and decision-making abilities in medical students.
The study will examine whether the AI-based evaluation system can provide reliable and valid assessments of medical students' performance in clinical scenarios. Participants will complete clinical case-based tasks designed to assess their clinical reasoning and decision-making abilities. Their responses will be evaluated using the AI-based system and compared with assessments made using established evaluation methods and/or expert ratings.
The findings of this study may help determine whether generative AI can be used as a practical tool for assessing clinical thinking and decision-making skills in medical education.
研究概览
详细说明
This study aims to develop and evaluate a generative artificial intelligence-based system for assessing clinical thinking and decision-making abilities in medical students. Clinical reasoning and decision-making are core competencies in medical education, but conventional assessment methods often require substantial faculty time and may be influenced by differences among evaluators.
The study will develop an intelligent evaluation framework using generative artificial intelligence to analyze medical students' responses to clinical case-based tasks. The system will assess key aspects of clinical thinking and decision-making, such as information interpretation, diagnostic reasoning, selection of appropriate management strategies, and overall decision-making logic.
Medical students participating in the study will complete standardized clinical scenarios or case-based assessment tasks. Their performance will be evaluated using the artificial intelligence-based system and compared with evaluations made by qualified clinical experts and/or established assessment methods. The study will examine the reliability, validity, consistency, and feasibility of the artificial intelligence-based evaluation approach.
The purpose of this study is to determine whether generative artificial intelligence can serve as a reliable and practical tool for evaluating clinical thinking and decision-making abilities in medical education. The system is intended for educational assessment and is not designed to replace clinical diagnosis or treatment decisions.
研究类型
注册 (实际的)
阶段
- 不适用
联系人和位置
学习地点
-
-
Zhejiang
-
Hangzhou、Zhejiang、中国、310000
- Sir Run Run Shaw Hospital, Zhejiang University School of Medicine
-
-
参与标准
资格标准
适合学习的年龄
接受健康志愿者
有资格学习的性别
描述
Inclusion Criteria:
- Aged 18 to 30 years.
- Fourth- or fifth-year undergraduate students majoring in Clinical Medicine at Zhejiang University School of Medicine, or trainees who have completed at least one year of standardized residency training at Sir Run Run Shaw Hospital, Zhejiang University School of Medicine.
- Have completed basic surgery courses and theoretical learning related to breast diseases.
- Voluntarily agree to participate in the study and provide written informed consent.
- Have adequate communication and comprehension abilities.
Exclusion Criteria:
- Have previously participated in similar generative artificial intelligence (GAI)-based teaching intervention studies.
- Are unable to complete the entire study because of rotation schedules or other conflicts.
- Belong to vulnerable populations other than employees of the study institution or subordinates of the investigators, including individuals with mental illness, cognitive impairment, critical illness, pregnancy, or illiteracy.
- Refuse or are unwilling to provide informed consent.
学习计划
研究是如何设计的？
设计细节
- 主要用途：其他
- 分配：随机化
- 介入模型：并行分配
- 屏蔽：单身的
武器和干预
参与者组/臂 |
干预/治疗 |
|---|---|
|
有源比较器：Control Group: Traditional Teaching
the standardized surgical oncology teaching curriculum, utilizing standardized breast cancer teaching PowerPoint courseware. |
Participants will receive standard traditional teaching, including routine classroom instruction, case-based learning, and teacher-guided discussion, without the use of the generative artificial intelligence-assisted learning component. |
|
实验性的：Intervention Group: Traditional Teaching Plus AI Assistance
the independently developed "Clinical Reasoning and Decision-Making Dialogue Evaluation System" on the basis of the same traditional teaching. |
Participants will receive standard traditional teaching, including routine classroom instruction, case-based learning, and teacher-guided discussion, without the use of the generative artificial intelligence-assisted learning component. The intervention consists of traditional medical education supplemented with a generative artificial intelligence-based learning tool. The tool will support students in clinical case analysis, reasoning, and decision-making exercises. The control group will receive the same traditional teaching without access to the AI-assisted learning component. |
研究衡量的是什么？
主要结果指标
结果测量 |
措施说明 |
大体时间 |
|---|---|---|
|
Change in Clinical Reasoning Score on Objective Structured Clinical Examination (OSCE)
大体时间：Baseline to Week 4
|
The total score ranges from 0 to 100. A higher score indicates better clinical thinking and decision-making ability |
Baseline to Week 4
|
次要结果测量
结果测量 |
措施说明 |
大体时间 |
|---|---|---|
|
Intraclass Correlation Coefficient (ICC) Between GAI-Based and Expert Assessment Scores
大体时间：Baseline to Week 4
|
Both Generative AI (GAI) and human experts will evaluate the participants using the clinical Reasoning Assessment Rubric. The agreement between the GAI-based scores and expert assessment scores will be evaluated using the Intraclass Correlation Coefficient (ICC) . The coefficient ranges from 0 to 1, where higher values indicate better agreement. |
Baseline to Week 4
|
|
Time to Complete the Assessment
大体时间：During the clinical thinking and decision-making assessment at Week 4 (completion time measured in minutes).
|
Assessment completion time is defined as the duration, measured in minutes, from the initiation of the clinical thinking and decision-making assessment to its final submission by the participant. The time will be automatically recorded by the evaluation platform. Each participant's assessment completion time will be measured during the assessment conducted at Week 4. |
During the clinical thinking and decision-making assessment at Week 4 (completion time measured in minutes).
|
|
Participant Satisfaction Score on the GAI-Assisted Evaluation System
大体时间：Week 4
|
Participant satisfaction will be measured using a 5-point Likert scale (ranging from 1 = Very Dissatisfied to 5 = Very Satisfied). A higher score indicates higher satisfaction with the GAI-assisted evaluation system. |
Week 4
|
合作者和调查者
研究记录日期
研究主要日期
学习开始 (实际的)
初级完成 (实际的)
研究完成 (实际的)
研究注册日期
首次提交
首先提交符合 QC 标准的
首次发布 (实际的)
研究记录更新
最后更新发布 (实际的)
上次提交的符合 QC 标准的更新
最后验证
更多信息
此信息直接从 clinicaltrials.gov 网站检索，没有任何更改。如果您有任何更改、删除或更新研究详细信息的请求，请联系 register@clinicaltrials.gov. clinicaltrials.gov 上实施更改，我们的网站上也会自动更新.