Trial · NCT07903467
Generative AI-Assisted Personalized Feedback for Laparoscopic Skill Learning in Medical Undergraduates
NCT07903467, Not applicable, Not yet recruiting, Yang Xiaodong
3 sourcestrials-2026-11-12-0.5.0
Download JSON
Cite this record
ConductScience Library. Generative AI-Assisted Personalized Feedback for Laparoscopic Skill Learning in Medical Undergraduates. Trials, record NCT07903467. Release trials-2026-11-12-0.5.0, 12 Nov 2026. https://conductscience.org/library/trials/NCT07903467
On this page
Trial
As registered on ClinicalTrials.gov, in the graph's capture of the registry.
- Title
- Generative AI-Assisted Personalized Feedback for Laparoscopic Skill Learning in Medical Undergraduates
- NCT number
- NCT07903467
- Status
- Not yet recruiting
- Phases
- Not applicable
- Enrollment
- 40 participants, estimated
- Lead sponsor
- Yang Xiaodong
- Conditions
- Medical Education
- Interventions
- Generative AI-Assisted Personalized Feedback, Structured Template-Based Feedback
- First posted
- 2026-10-29
- Last updated
- 2026-10-30
Source ClinicalTrials.gov
Registered outcomes10
Each outcome the trial registered, primary first, in ClinicalTrials.gov's words.
| List | Outcome | Time frame | Description |
|---|---|---|---|
| Primary | Fundamentals of Laparoscopic Surgery Precision Cutting-Derived Objective Score (PCOS) at T4 | Immediately after completion of the cutting training phase (T4), approximately 4 weeks after baseline. | Precision cutting performance will be assessed using the study-defined Precision Cutting Objective Score derived from the Fundamentals of Laparoscopic Surgery task. PCOS = max(0, 300 - T - 100 × Aerror/Atarget), where T is completion time in seconds, Aerror is the exclusive-or area between the target and actual cutting contours, and Atarget is the target area. Scores range from 0 to 300; higher scores indicate better performance. Incomplete tasks or completion times of 300 seconds or longer receive 0. Technically unevaluable assessments are treated as missing. This is a research score, not an official FLS certification score. |
| Secondary | Fundamentals of Laparoscopic Surgery Peg Transfer-Derived Objective Score (PTOS) at T2 | Immediately after completion of the transfer training phase (T2), approximately 2 weeks after baseline. | Peg transfer performance will be assessed using the study-defined Peg Transfer Objective Score derived from the Fundamentals of Laparoscopic Surgery task. PTOS = max(0, 300 - T - 100 × Nlost/6), where T is completion time in seconds and Nlost is the number of irretrievable objects. Scores range from 0 to 300; higher scores indicate better performance. Incomplete tasks or completion times of 300 seconds or longer receive 0. Recoverable drops do not incur an additional direct penalty. Technically unevaluable assessments are treated as missing. This is a research score, not an official FLS certification score. |
| Secondary | Transfer Training Task Performance Assessed With the Task-Specific Behaviorally Anchored Rating Scale (TS-BARS) | Baseline (T0), approximately week 1 (T1), and approximately week 2 (T2). | Learning progression on the 14-ball transfer training task will be assessed using the study-specific Task-Specific Behaviorally Anchored Rating Scale. Seven domains are scored from 0 to 5, yielding a total score of 0-35; higher scores indicate better technical performance. The mean of two independent masked assessors' valid total scores will be used after any required discrepancy review. Repeated total scores will characterize the training trajectory. |
| Secondary | Cutting Training Task Performance Assessed With the Task-Specific Behaviorally Anchored Rating Scale (TS-BARS) | Approximately week 2 (T2), week 3 (T3), and week 4 (T4) after baseline. | Learning progression on the study-developed shape-cutting training task will be assessed using the study-specific Task-Specific Behaviorally Anchored Rating Scale. Seven domains are scored from 0 to 5, yielding a total score of 0-35; higher scores indicate better technical performance. The mean of two independent masked assessors' valid total scores will be used after any required discrepancy review. Repeated total scores will characterize the training trajectory. |
| Other | Precision Cutting Skill Retention Assessed With the Precision Cutting Objective Score (PCOS) at T5 | T5, 4-8 weeks after T4, approximately 8-12 weeks after baseline. | Retention will be assessed by repeating the Fundamentals of Laparoscopic Surgery Precision Cutting task and calculating the study-defined Precision Cutting Objective Score: max(0, 300 - completion time in seconds - 100 × error area/target area). Scores range from 0 to 300; higher scores indicate better retained performance. The same completion, time-limit, and evaluability rules used for the T4 assessment will apply. |
| Other | Peg Transfer Skill Retention Assessed With the Peg Transfer Objective Score (PTOS) at T5 | T5, 4-8 weeks after T4, approximately 8-12 weeks after baseline. | Retention will be assessed by repeating the Fundamentals of Laparoscopic Surgery Peg Transfer task and calculating the study-defined Peg Transfer Objective Score: max(0, 300 - completion time in seconds - 100 × number of irretrievable objects/6). Scores range from 0 to 300; higher scores indicate better retained performance. The same completion, time-limit, and evaluability rules used for the T2 assessment will apply. |
| Other | Transfer Training Self-Assessment Absolute Calibration Error Relative to TS-BARS Ratings at T2 | At the end of the transfer training phase (T2), approximately 2 weeks after baseline. | Self-assessment accuracy will be quantified as the mean absolute difference between the learner's domain-level self-ratings and the corresponding mean ratings from two independent assessors using the Task-Specific Behaviorally Anchored Rating Scale for the transfer training task. Each comparable domain is rated from 0 to 5. Absolute calibration error ranges from 0 to 5; lower values indicate more accurate self-assessment. |
| Other | Cutting Training Self-Assessment Absolute Calibration Error Relative to TS-BARS Ratings at T4 | At the end of the cutting training phase (T4), approximately 4 weeks after baseline. | Self-assessment accuracy will be quantified as the mean absolute difference between the learner's domain-level self-ratings and the corresponding mean ratings from two independent assessors using the Task-Specific Behaviorally Anchored Rating Scale for the cutting training task. Each comparable domain is rated from 0 to 5. Absolute calibration error ranges from 0 to 5; lower values indicate more accurate self-assessment. |
| Other | Study-Specific Feedback Satisfaction and Acceptability Questionnaire Item Scores | At the end of the transfer phase (T2, approximately week 2) and cutting phase (T4, approximately week 4). | Learners' perceptions of the feedback actually received will be assessed using the study-specific, source-neutral, eight-item Feedback Satisfaction and Acceptability Questionnaire. Each item is scored from 1 to 5, with higher scores indicating greater satisfaction or acceptability after any prespecified reverse coding. Item scores will be reported separately at each assessment. The questionnaire will not identify the feedback source or ask about AI-specific acceptance. |
| Other | Study-Specific Feedback Quality Rating Rubric Domain Scores for Paired AI and Template Candidates | At four feedback-generation events based on baseline (T0) and approximately weeks 1, 2, and 3 (T1-T3) assessments. | First-attempt, unedited AI and template feedback candidates generated from identical frozen inputs will be evaluated offline by two independent source-masked raters using the study-specific Feedback Quality Rating Rubric. Domains are grounding, prioritization, specificity, actionability, goal clarity, longitudinal coherence, and information economy. Each domain is rated from 1 to 5; higher scores indicate better quality. The mean of the two raters' scores will be reported separately for each domain. Longitudinal coherence is assessed only for second-feedback events within each task phase. Undelivered candidates are used only for the offline comparison and are not linked to learner reception or subsequent performance. |
Source ClinicalTrials.gov
Outcomes0
Each outcome the trial posted results for, in ClinicalTrials.gov's words.
None in this release.
Results by group0
Each measurement the trial posted, group by group, in the words and numbers it posted.
None in this release.
Participant flow0
How many started, completed or left each group, period by period.
None in this release.
Adverse events0
Each adverse event the trial posted, group by group: the participants affected out of those at risk.
None in this release.
Adverse event totals0
The totals the trial posted for each group.
None in this release.
Papers4
The papers the trial lists on ClinicalTrials.gov.
Grants0
The grants NIH RePORTER links to the trial, newest funded first: NIH's, and some of AHRQ's, CDC's, FDA's and VA's. Each shows its title, principal investigators, organization and funder in its newest year.
None in this release.
Trial comparisons0
Comparisons of the trial's two groups, calculated by ConductScience from the counts it posted.
None in this release.
Tests0
The ConductCognition tests this trial's registered outcomes name, as ScienceGraph matched them in trial-tests-2026-11-12-0.2.1.
None in this release.
Data dates
The day each source was copied for this release.
Sources 3
- ClinicalTrials.gov's posted results, through CTTI's AACTFreely available. Acknowledgement requested
- ClinicalTrials.govNo license stated
- NIH RePORTER's clinical studies and project filesPublic domain
Each source's terms
- ClinicalTrials.gov's posted results, through CTTI's AACTClinicalTrials.gov data via Aggregate Analysis of ClinicalTrials.gov (AACT), CTTI. CTTI makes its materials freely available and requests acknowledgement. https://aact.ctti-clinicaltrials.org/documentation/299
- ClinicalTrials.govnone stated
- NIH RePORTER's clinical studies and project filesPublic domain (NIH RePORTER)
ClinicalTrials.gov's data carry an international copyright outside the United States: https://clinicaltrials.gov/about-site/terms-conditions.
For software
Read this trial from software.
The record and each of its lists are JSON, twenty rows a page. No key.
GET https://conductscience.org/api/trials/v1/NCT07903467
GET https://conductscience.org/api/trials/v1/NCT07903467/registered