Intelligent Simulated Patient System for Gastroenterology Education
NCT07714655 · Status: COMPLETED · Phase: NA · Type: INTERVENTIONAL · Enrollment: 90
Last updated 2026-08-06
Summary
This randomized controlled trial evaluated a large language model-based Intelligent Simulated Patient System (ISPS) for gastroenterology history-taking education. Ninety medical students were randomly assigned in a 1:1 ratio to 4 weeks of conventional clinical learning or ISPS-assisted training.
The ISPS used teacher-defined structured case information to support simulated patient interactions and generated item-level formative feedback using predefined scoring rubrics. The implemented system did not use external electronic health record retrieval, retrieval-augmented generation, a vector database, or semantic-similarity threshold scoring.
The primary outcomes were post-intervention medical history-taking performance and clinical diagnostic accuracy. History-taking performance was assessed in a standardized Objective Structured Clinical Examination by two senior physicians who were blinded to group allocation. Secondary outcomes included patient-centered communication competence and participants' acceptance of the ISPS.
Conditions
- Medical Education
- Clinical Competence
- History Taking
Interventions
- OTHER
-
Intelligent Simulated Patient System (ISPS)
Participants received 4 weeks of self-directed gastroenterology history-taking training using the Intelligent Simulated Patient System (ISPS). Participants selected teacher-configured clinical cases and conducted multiround history-taking interviews with large language model-driven simulated patients. Simulated-patient responses were constrained by teacher-defined structured patient information. After each training encounter, the ISPS evaluated history-taking completeness item by item using a predefined 100-point Medical History-Taking Assessment rubric and provided individualized formative feedback. Patient-centered communication competence was assessed separately from the complete interview transcript using a four-domain scale. These automated scores and feedback were used solely for formative training and were not used as the primary post-intervention outcome of the randomized trial. In the system version evaluated in this study, case information and scoring criteria were configure
- OTHER
-
Conventional Clinical Teaching
Participants received conventional clinical education for four weeks, including bedside teaching, case-based learning, paper-based medical record review, and faculty-guided clinical discussions according to the standard curriculum.
Sponsors & Collaborators
-
The First Affiliated Hospital of Zhejiang Chinese Medical University
lead OTHER
Study Design
- Allocation
- RANDOMIZED
- Purpose
- OTHER
- Masking
- SINGLE
- Model
- PARALLEL
Eligibility
- Min Age
- 18 Years
- Sex
- ALL
- Healthy Volunteers
- Yes
Timeline & Regulatory
- Start
- 2026-03-01
- Primary Completion
- 2026-06-01
- Completion
- 2026-06-01
Countries
- China
Study Locations
More Related Trials
-
Artificial Intelligence for Determination of Gastroscopy Surveillance Intervals
NCT05631015 ·Status: UNKNOWN
-
A Study on the Effectiveness of AI-assisted Colonoscopy in Improving the Effect of Colonoscopy Training for Trainees
NCT04912037 ·Status: UNKNOWN ·Phase: NA
-
Using Simulation to Ensure Basic Competence in Gastroscopy
NCT04150237 ·Status: COMPLETED
-
Real-Time Identification System of Magnetically Controlled Capsule Endoscopy Using Artificial Intelligence
NCT04203264 ·Status: UNKNOWN
-
Applying Gamification to Postgraduate Endoscopic Training
NCT03176251 ·Status: COMPLETED ·Phase: NA
-
Efficacy of an AI System in Training Endoscopists to Assess Gastric Intestinal Metaplasia Via the EGGIM Score
NCT07208864 ·Status: NOT_YET_RECRUITING ·Phase: NA
-
Artificial Intelligence-Assisted Training for Novice Physicians in Electronic Nasopharyngolaryngoscopy
NCT07726641 ·Status: NOT_YET_RECRUITING ·Phase: NA
-
A Multi-Center Randomized Controlled Trial on the Impact of Disease Subtype-Based Active Video Education on Bowel Preparation Quality in Patients With Inflammatory Bowel Disease
NCT07582731 ·Status: NOT_YET_RECRUITING ·Phase: NA
-
Deep Learning Algorithm for the Diagnosis of Gastrointestinal Diseases
NCT04222439 ·Status: UNKNOWN ·Phase: NA
-
A Cohort Study of Mobile Capsule Gastroscopy for Gastric Pathologies Screening
NCT07032961 ·Status: RECRUITING
-
Artificial Intelligence vs Endoscopist Identification in EUS Normal Anatomy
NCT06279546 ·Status: COMPLETED
-
A Multicentric Validation Study on the Accuracy of Artificial Intelligence Assisted System in Clinical Application of Digestive Endoscopy
NCT04232462 ·Status: ACTIVE_NOT_RECRUITING
-
Automatic Real-time Diagnosis of Gastric Mucosal Disease Using pCLE With Artificial Intelligence
NCT03784209 ·Status: COMPLETED
-
NLP to Aid in the Evaluation and Diagnosis of FGIDs
NCT05501028 ·Status: ENROLLING_BY_INVITATION
-
Gastrointestinal Endoscopy Artificial Intelligence Cloud Platform in Gastrointestinal Endoscopy Screening
NCT05435872 ·Status: UNKNOWN ·Phase: NA
-
Learning Curves of Gastric Ultrasound for Novel
NCT04760106 ·Status: UNKNOWN
-
AI Assistance in GI Endoscopy Recovery Assessment
NCT06923059 ·Status: NOT_YET_RECRUITING ·Phase: NA
-
AI-Driven Multimodal Imaging Integration for Diagnosis and Prognostication of Digestive System Diseases
NCT07087418 ·Status: RECRUITING
-
The Impact of Comprehensive Education Before Gastroscopy on Improving the Tolerance of Patients
NCT03638752 ·Status: COMPLETED ·Phase: NA
-
Impact of a Simulation-based Training Curriculum of Non-technical Skills on Colonoscopy Performance
NCT02877420 ·Status: COMPLETED ·Phase: NA
-
Evaluation of the Clinical Effectiveness of Upper Gastrointestinal Endoscopy Reporting System
NCT05851885 ·Status: UNKNOWN ·Phase: NA
-
Simulation-assisted Teaching in Learning Gastroscopy
NCT04247399 ·Status: COMPLETED ·Phase: NA
-
Artificial Intelligence in Assessing Gastric Intestinal Metaplasia Via the EGGIM Score
NCT07257796 ·Status: RECRUITING
-
Upper Gastrointestinal Endoscopy Reporting System in Improving Report Quality
NCT05851716 ·Status: UNKNOWN
-
Performance of Artificial Intelligence Tools and Ultrasonographers With Different Skills
NCT05823792 ·Status: UNKNOWN