Medical EducationAIFB-NRNCT07871526
AI-Generated and Rule-Based Individualized Feedback for Medical Students' Nephrology Learning
A study testing AI-Generated Individualized Feedback, Rule-Based Individualized Feedback and No Individualized Feedback in people with Medical Education, run by Dou Fulin at 1 site in China.
Trial summary
Medical education increasingly emphasizes individualized learning and formative assessment; however, providing timely and personalized feedback to students remains challenging because of limited faculty resources. Read more about this study
- Who is it for?
- Ages 18 years and olderHealthy volunteers can take part
- Conditions the study is for
- Medical Education
- What is being tested?
- AI-Generated Individualized Feedback, Rule-Based Individualized Feedback and No Individualized Feedback
- Type of treatment
- Lifestyle or therapy programme
- Could I receive a placebo?
- No, everyone receives an active treatment
- How many people
- 190 participants
- Where
- 1 siteChina
- Study dates
- 15 Oct 2026to 28 Feb 2027
- Phase
- Interventional
Key requirements
Who can take part, as listed by the sponsor. Only the study team can confirm whether you are eligible, so take this list to your doctor.
- Ages 18 years and older
- All sexes
- Healthy volunteers accepted
- Adult, Older adult
Who may be able to join
- Undergraduate medical students participating in the nephrology clerkship at The Second Qilu Hospital of Shandong University.
- Students who voluntarily agree to participate in the study and provide informed consent.
- Students who complete the baseline assessment and follow the study procedures.
Who cannot join
- Students who do not complete the required assessments or withdraw from the study.
- Students who have previously participated in the same nephrology feedback intervention study.
- Students who are unable to complete the study procedures due to personal reasons.
Trial locations and contacts
1 site in 1 country. Contact the study team or a site near you to ask about taking part.
China1 site
The Second Qilu Hospital of Shandong University
Jinan, Shandong, 250033
Fulin Dou, +86 18660799813, doufu@email.sdu.edu.cn
Xiaodong Yang, +86 17660084456, yangxiao@email.sdu.edu.cn
About this study
Official title: Effect of Pretest-Based Individualized Feedback on Learning Outcomes of Medical Students During Nephrology Clerkship: A Three-Arm Cluster Randomized Controlled Trial Comparing AI-Generated Feedback, Rule-Based Feedback, and No Feedback
Medical education increasingly emphasizes individualized learning and formative assessment; however, providing timely and personalized feedback to students remains challenging because of limited faculty resources. Generative artificial intelligence (AI) may provide a scalable approach for generating individualized feedback based on students' learning needs, but its educational effectiveness compared with traditional feedback approaches remains uncertain.
This study is a single-center, prospective, three-arm, cluster randomized controlled trial designed to evaluate the effect of pretest-based individualized feedback on medical students' learning outcomes during a nephrology clerkship. Undergraduate medical students participating in a nephrology clerkship at The Second Qilu Hospital of Shandong University will be recruited and assigned by teaching class clusters to one of three groups: an AI-generated feedback group, a rule-based individualized feedback group, or a no-feedback control group.
Read more
All participants will receive the same nephrology clerkship teaching based on the BOPPPS-CBL instructional model. Before the clerkship, students will complete a diagnostic pretest. Based on the pretest results, individualized feedback will be provided according to group allocation. The primary outcome is immediate knowledge acquisition assessed by the post-test score immediately after the clerkship. Secondary outcomes include four-week knowledge retention, knowledge gap remediation, and clinical reasoning performance.
This study aims to determine whether AI-generated individualized feedback provides additional educational benefits compared with traditional rule-based feedback and no feedback, and to provide evidence for the application of artificial intelligence-assisted personalized learning in medical education.
Read the detailed description
Background
Individualized feedback is an important component of formative assessment in medical education. Effective feedback can help learners identify knowledge gaps, regulate learning strategies, and improve academic performance. However, delivering timely and personalized feedback to a large number of medical students is challenging because it requires substantial faculty time and expertise.
Recent advances in generative artificial intelligence (AI) provide new opportunities for scalable personalized feedback generation. AI systems may analyze learners' performance patterns and generate targeted feedback based on individual learning needs. Nevertheless, evidence regarding whether AI-generated feedback improves learning outcomes beyond conventional rule-based feedback approaches remains limited, particularly in clinical medical education settings.
Objective
The objective of this study is to evaluate the effectiveness of pretest-based individualized feedback on medical students' learning outcomes during a nephrology clerkship. Specifically, the study aims to compare AI-generated individualized feedback, rule-based individualized feedback, and no feedback regarding immediate knowledge acquisition, four-week knowledge retention, knowledge gap remediation, and clinical reasoning performance.
Study Design
This is a single-center, prospective, three-arm, parallel-group, cluster randomized controlled educational intervention study. The unit of randomization will be the teaching class cluster. Approximately 190 undergraduate medical students participating in nephrology clerkship at The Second Qilu Hospital of Shandong University will be enrolled.
Twelve natural teaching classes will be allocated in a 1:1:1 ratio to three study groups:
AI-generated feedback group; Rule-based individualized feedback group; No-feedback control group.
Randomization will be performed using a computer-generated random allocation sequence by an independent individual not involved in teaching or outcome assessment.
Intervention
Before the nephrology clerkship, all participants will complete a diagnostic pretest (A questionnaire) assessing baseline knowledge. According to the assigned intervention group, students will receive different feedback approaches.
In the AI-generated feedback group, individualized feedback will be generated based on students' pretest results using a structured prompt framework. The feedback will include identified knowledge weaknesses, related learning recommendations, and targeted suggestions. AI-generated feedback will be reviewed by nephrology faculty before being provided to students.
In the rule-based individualized feedback group, feedback will be generated using a predefined mapping system linking test items, knowledge domains, error types, and corresponding feedback modules.
In the no-feedback control group, students will not receive individualized feedback after completing the pretest. They will receive the same subsequent nephrology clerkship teaching as other groups.
All groups will participate in the same BOPPPS-CBL-based nephrology clerkship teaching activities.
Outcome Measures
The primary outcome is immediate knowledge acquisition, measured by the total score of the B questionnaire (0-100 points) immediately after completion of the nephrology clerkship.
Secondary outcomes include:
Four-week knowledge retention, assessed by the total score of the C questionnaire (0-100 points) four weeks after the clerkship; Knowledge gap remediation, evaluated by changes in performance on previously identified weak knowledge areas; Clinical reasoning performance assessed using structured clinical reasoning evaluation methods.
Statistical Analysis
The primary analysis will use a linear mixed-effects model with post-test score as the dependent variable, intervention group as a fixed effect, teaching class as a random effect, and baseline pretest score as a covariate. Between-group comparisons will be performed with adjustment for multiple comparisons when appropriate.
Significance
This study will provide evidence regarding the educational value of AI-generated individualized feedback compared with conventional feedback approaches. The findings may contribute to the development of scalable, personalized learning strategies and support the integration of artificial intelligence into medical education.
- Conditions
- Medical Education
- Being tested
- AI-Generated Individualized Feedback, Rule-Based Individualized Feedback, No Individualized Feedback
- Keywords
- Generative Artificial Intelligence, Artificial Intelligence, Individualized Feedback, Personalized Learning, Nephrology Clerkship
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
AI-Generated Individualized FeedbackBehavioural
Participants receive individualized feedback generated using generative artificial intelligence based on their pretest performance. Before the nephrology clerkship, students complete a diagnostic pretest. Their incorrect responses and knowledge gaps are analyzed, and AI-generated feedback is produced using a structured prompt framework. The generated feedback includes identified learning gaps, explanations, and targeted learning recommendations. All AI-generated feedback is reviewed by nephrology faculty before being provided to students.
Rule-Based Individualized FeedbackBehavioural
Participants receive individualized feedback generated using a predefined rule-based feedback system based on their pretest performance. The system links test items, knowledge domains, error types, and corresponding feedback modules to generate targeted learning recommendations. Feedback content is reviewed before being provided to students. Participants subsequently receive the same nephrology clerkship teaching as other study groups.
No Individualized FeedbackBehavioural
Participants complete the diagnostic pretest but do not receive individualized feedback, explanations, or learning recommendations based on their test results before the nephrology clerkship. They receive the same BOPPPS-CBL nephrology clerkship teaching as participants in the other study groups.
| Study group | Role | What they receive |
|---|---|---|
| AI-Generated Individualized Feedback Group | Experimental | Participants in this group will receive AI-generated individualized feedback based on their pretest performance before the nephrology clerkship. A diagnostic pretest will be administered before the intervention. Based on identified knowledge gaps, generative artificial intelligence will generate personalized feedback using a structured prompt framework. The AI-generated feedback will be reviewed by nephrology faculty before being provided to students. Participants will then receive the same BOPPPS-CBL nephrology clerkship teaching as other groups. Receives: Behavioral: AI-Generated Individualized Feedback |
| Rule-Based Individualized Feedback Group | Experimental | Participants in this group will receive rule-based individualized feedback generated from their pretest performance before the nephrology clerkship. Feedback will be created using a predefined mapping system linking test items, knowledge domains, error types, and corresponding feedback modules. Participants will then receive the same BOPPPS-CBL nephrology clerkship teaching as other groups. Receives: Behavioral: Rule-Based Individualized Feedback |
| No Feedback Control Group | Active comparator | Participants in this group will complete the diagnostic pretest but will not receive individualized feedback, explanations, or learning recommendations based on their test results before the nephrology clerkship. Participants will receive the same BOPPPS-CBL nephrology clerkship teaching as the other groups. Receives: Behavioral: No Individualized Feedback |
What is being measured
The primary outcome is the main question the study is designed to answer.
Immediate Knowledge Acquisition
Immediate knowledge acquisition will be assessed using the total score of the post-intervention nephrology knowledge test (B questionnaire), administered immediately after completion of the nephrology clerkship. The B questionnaire is a parallel-form knowledge assessment based on the same predefined assessment blueprint as the baseline and delayed tests. The total score is converted to a 0-100 scale, with higher scores indicating greater knowledge acquisition.
Measured: Immediately after completion of the nephrology clerkship
Secondary outcomes (3)
Four-Week Knowledge Retention
Knowledge retention will be assessed using the total score of the delayed nephrology knowledge test (C questionnaire), administered four weeks after completion of the nephrology clerkship. The C questionnaire is a parallel-form assessment based on the same predefined assessment blueprint as the A and B questionnaires. The total score is converted to a 0-100 scale, with higher scores indicating better retention of nephrology knowledge.
Measured: 4 weeks after completion of the nephrology clerkship
Knowledge Gap Remediation
Knowledge gap remediation will be assessed among knowledge points that were answered incorrectly on the baseline A questionnaire and had a pre-specified parallel knowledge-point item on the post-intervention B questionnaire. For each participant, the knowledge gap remediation rate will be calculated as the proportion of these previously incorrect knowledge points that are answered correctly on the corresponding B questionnaire items. The outcome ranges from 0% to 100%, with a higher percentage indicating greater remediation of baseline knowledge gaps.
Measured: Immediately after completion of the nephrology clerkship
Knowledge Gain
Immediate knowledge gain will be assessed as the change in total knowledge test score from baseline to immediately after the clerkship, calculated as the B questionnaire total score minus the A questionnaire total score (B-A). Both scores are expressed on a 0-100 scale. A higher positive value indicates greater improvement in nephrology knowledge from baseline.
Measured: Immediately after completion of the nephrology clerkship
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted13 Oct 2026
- Study start15 Oct 2026 (estimated)
- Primary completion31 Dec 2026 (estimated)
- Study completion28 Feb 2027 (estimated)
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Other trials for Medical EducationStudies of the same condition, open and under way.
- What the trial phases meanHow a treatment moves from first tests in people to approval.
More details
For doctors and researchers: how the study is designed, who runs it, and its registry IDs.
Study design
- Study type
- Interventional
- Phase
- Phase N/A
- Primary purpose
- Other
- Allocation
- Randomised
- Intervention model
- Parallel groups
- Model description
- Participants will be assigned to one of three parallel groups using cluster randomization at the teaching-class level: AI-generated individualized feedback group, rule-based individualized feedback group, and no-feedback control group. All groups will receive the same nephrology clerkship teaching based on the BOPPPS-CBL model.
- Masking
- Single blind
- Who is masked
- Outcomes assessor
- Enrolment
- 190 participants (estimated)
Sponsor and investigators
- Lead sponsor
- Dou Fulin
- Sponsor type
- University, hospital or other
- Responsible party
- Sponsor-investigator, Dou Fulin, The Second Hospital of Shandong University
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT07871526
- Sponsor's protocol ID
- DFL-AIFB-2026
- Other IDs
- KYLL20260138
- Acronym
- AIFB-NR
- Status last verified
- Oct 2026
- First submitted
- 7 Oct 2026
- Last updated
- 16 Oct 2026
- Results posted
- No
- Data monitoring committee
- No
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- Yes: De-identified individual participant data (IPD) underlying the results reported in the primary publication may be shared with qualified researchers upon reasonable request. The shared data may include participant baseline characteristics, intervention allocation, questionnaire scores, and outcome measures. Data will be provided after publication of the primary results and after approval by the principal investigator.