Generative AI-Based Evaluation of Clinical Thinking and Decision-Making in Medical Students

October 30, 2026 updated by: Danzhi Chen, Sir Run Run Shaw Hospital

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.

Study Overview

Status

Completed

Conditions

Intervention / Treatment

Detailed Description

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.

Study Type

Interventional

Enrollment (Actual)

90

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

  • China
    • Zhejiang
      • Hangzhou, Zhejiang, China, 310000
        • Sir Run Run Shaw Hospital, Zhejiang University School of Medicine

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

18 years to 30 years (Adult)

Accepts Healthy Volunteers

No

Genders Eligible for Study

All

Description

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.

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: Single

Arms and Interventions

Participant Group / Arm
Intervention / Treatment
Active Comparator: Control Group: Traditional Teaching

the standardized surgical oncology teaching curriculum, utilizing standardized breast cancer teaching PowerPoint courseware.
Behavioral: 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.
Experimental: 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.
Behavioral: 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.

Behavioral: AI-Assisted Teaching

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.

What is the study measuring?

Primary Outcome Measures

Outcome Measure
Measure Description
Time Frame
Change in Clinical Reasoning Score on Objective Structured Clinical Examination (OSCE)
Time Frame: 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

Secondary Outcome Measures

Outcome Measure
Measure Description
Time Frame
Intraclass Correlation Coefficient (ICC) Between GAI-Based and Expert Assessment Scores
Time Frame: 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
Time Frame: 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
Time Frame: 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

Collaborators and Investigators

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

Sponsor

Sir Run Run Shaw Hospital

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 26, 2025

Primary Completion (Actual)

December 25, 2025

Study Completion (Actual)

December 25, 2025

Study Registration Dates

First Submitted

October 9, 2026

First Submitted That Met QC Criteria

October 30, 2026

First Posted (Actual)

November 4, 2026

Study Record Updates

Last Update Posted (Actual)

November 4, 2026

Last Update Submitted That Met QC Criteria

October 30, 2026

Last Verified

October 1, 2026

More Information

Terms related to this study

Keywords

Other Study ID Numbers

  • Research 2025734

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.

Subscribe