Generative AI-Assisted Understanding and Decision Enhancement in Peritoneal Dialysis: A Randomized Controlled Trial (The GUIDE-PD Trial)
Trial Snapshot
- Phase
- Not Applicable
- Status
- Enrolling By Invitation
- Sponsor
- Enrollment
- 100
- Locations
- 1
- Primary Endpoint
- Management Reasoning
Study Overview
Brief Summary
This study is a randomized controlled trial based on simulated clinical cases, aiming to establish a standardized evaluation system for PD physicians, to assess the differences in PD management quality between a workflow assisted by a PD-specialized large language model and physician-only decision-making, and to identify potential risks (such as generating obviously erroneous or even harmful recommendations). This simulated clinical case framework not only supports standardized and blinded evaluation, but also provides preliminary evidence for the model's effectiveness and safety before its deployment in real clinical settings, while avoiding direct impact on real patients.
Study Design
- Study Type
- Interventional
- Allocation
- Randomized
- Intervention Model
- Parallel
- Primary Purpose
- Treatment
- Masking
- Single (Outcomes Assessor)
Eligibility Criteria
- Sex
- All
- Accepts Healthy Volunteers
- Yes
Inclusion Criteria
- •Internal medicine or nephrology standardized training residents, licensed residents, or attending physicians.
- •Independent experience in PD management ≤ 3 years.
- •Provided signed informed consent and agreed to comply with the trial procedures.
Exclusion Criteria
- •Direct involvement in the development or training of the specialized PD large language model, or in the construction of the clinical scenarios/ scoring criteria used in this trial.
- •Participation in the pilot testing of all clinical scenarios used in this trial.
- •Inability or unwillingness to access the study platform or use online resources during the study period.
- •Experienced PD experts.
Outcomes
Primary Outcomes
Management Reasoning
Time Frame: Within the 120-minute test period of the first test.
Percent correct (range: 0 to 100) for each case.
Secondary Outcomes
- Self-Reported Confidence per Case(Within the 120-minute test period of the first test.)
- Domain-Specific Scores(Within the 120-minute test period of the first test.)
- Severity of Potential Harm(Within the 120-minute test period of the first test.)
- Time per Scenario Case(Within the 120-minute test period of the first test.)
- Difference between the Phys group's scores when tested with PD-LLM assistance and when assisted only by traditional search methods(After 1-2 months of washout of first test)
Investigators
Wei Chen
Vice President
First Affiliated Hospital, Sun Yat-Sen University