Generative AI-Based Immersive Training for Endodontic Risk Disclosure and Informed Consent Among Dental Students (GAI-ENDORDIC)

Generative AI-Based Immersive Training for Endodontic Risk Disclosure and Informed Consent Among Dental Students: A Randomized Controlled Trial

The objective of this prospective, parallel-group, 1:1 randomized controlled trial is to evaluate the effectiveness of a generative artificial intelligence (AI)-based immersive training program, utilizing the Gemini platform, in improving endodontic risk disclosure and informed consent (RD-IC) quality, communication competence, self-efficacy, and reducing communication anxiety among undergraduate dental students during their clinical clerkship.

Traditional pedagogical methods in dental education, such as case-based learning (CBL) and peer role-playing, often struggle to simulate the high-stakes interpersonal tension and technical complexity involved in specialized endodontic risk disclosure. Complications like instrument separation, pulp floor perforation, and acute flare-ups require clear, empathetic, and legally sound communication. While standardized patients (SPs) are effective, they pose severe logistical and financial constraints for large student cohorts.

To address this gap, 96 fifth-year undergraduate dental students undergoing clinical rotation were recruited and randomly allocated to either the experimental group (1-month generative AI-based immersive training via the Gemini platform) or the control group (1-month conventional case-based learning). The AI intervention provided interactive, real-time conversational simulations across six high-stakes endodontic clinical scenarios, delivering instantaneous, personalized feedback on technical accuracy and empathetic delivery.

The primary outcome evaluated was the RD-IC completeness score. Secondary outcomes included SEGUE communication framework scores, Self-Efficacy in Clinical Communication Scale (SCS) scores, Communication Anxiety Scale (CAS) scores, blinded standardized patient (SP) ratings, user satisfaction, and long-term clinical skill retention assessed at 1-month (T2-1m) and 2-month (T2-2m) post-intervention follow-ups.

Study Overview

• Status: Completed
• Conditions: Informed Consent; Clinical Communication; Endodontic Diseases
• Intervention / Treatment: Other: Generative AI-Based Immersive Training; Other: Conventional Case-Based Learning

Detailed Description

BACKGROUND AND RATIONALE:

Endodontic treatments-including root canal therapy, retreatment, and periradicular surgery-are technically demanding procedures that carry inherent risks of irreversible complications, such as instrument separation, canal ledging, pulp floor perforation, and acute flare-ups. Effective risk disclosure and informed consent (RD-IC) processes are essential ethical and legal safeguards that ensure patient autonomy, foster collaborative doctor-patient trust, and minimize medicolegal hazards. However, traditional dental education relying on passive lectures or case-based learning (CBL) fails to recreate the real-world psychological pressure and conversational fluidity needed during challenging consultations. Generative AI large language models (LLMs), such as Gemini, offer an innovative, highly scalable "safe-to-fail" platform capable of simulating adaptive patient personas with diverse emotional profiles and health literacy levels.

STUDY DESIGN AND PARTICIPANT RECRUITMENT:

This prospective, parallel-group, 1:1 randomized controlled trial was conducted at the Department of Stomatology, The First Affiliated Hospital of Hunan University of Chinese Medicine, from March to May 2026. The trial protocol strictly adhered to the CONSORT 2010 statement and CONSORT-EHEALTH 2023 extension guidelines, with ethical approval granted by the Institutional Review Board (Ethics File No. MR-43-26-046512).

A total of 96 eligible fifth-year undergraduate dental students in their clinical clerkship who had completed core endodontic didactic courses were enrolled. Participants were randomly assigned via a computer-generated random sequence to either:

1. Experimental Group (n=48): Generative AI-based Immersive Training.
2. Control Group (n=48): Conventional Case-Based Learning (CBL).

EDUCATIONAL INTERVENTIONS:

• Experimental Group: Participants completed a 1-month simulation program using the Gemini platform. The curriculum comprised six standardized, high-stakes endodontic clinical scenarios (including acute pain management, instrument separation disclosure, and pulp floor perforation). Students engaged in 10-15 minute adaptive dialogue sessions every 3-4 days. The platform utilized standardized prompt templates to deliver real-time, objective feedback on both technical completeness (risk disclosure) and humanistic communication (empathy, tone, and clarity).
• Control Group: Participants underwent conventional CBL targeting the exact same six endodontic scenarios over the same 1-month duration. Learning involved structured group case discussions, faculty lectures, and standard informed consent document reviews. Both groups had equal access to standard clinical guidelines.

OUTCOME MEASURES AND DATA COLLECTION:

Assessments were conducted at four distinct time points: Baseline (T0), Immediately Post-Intervention (T1), 1-Month Follow-Up (T2-1m), and 2-Month Follow-Up (T2-2m).

1. Primary Outcome: RD-IC Completeness Score, measured via a validated 10-item checklist covering core indications, intraoperative complications, post-op pain, prognosis, alternative plans, and compliance.

2. Secondary Outcomes:

   • SEGUE Framework Scores: Assessing systematic communication competence (Set the stage, Elicit info, Give info, Understand perspective, End encounter).
   • Communication Self-Efficacy Scale (SCS) Scores: Evaluating confidence across clinical communication domains.
   • Communication Anxiety Scale (CAS) Scores: Assessing psychological tension and situational anxiety.
   • Blinded Standardized Patient (SP) Global Ratings: External validation of clinical communication performance.
   • Training Satisfaction Questionnaire: Evaluating platform authenticity, feedback quality, and user experience.
   • Longitudinal Retention: Skill retention and clinical transferability evaluated at T2-1m and T2-2m.

STATISTICAL ANALYSIS:

Data analysis was conducted using SPSS 26.0 following Intention-To-Treat (ITT) and Per-Protocol (PP) principles. Group differences were evaluated using t-tests, Mann-Whitney U tests, chi-square tests, and repeated-measures ANOVA, with Bonferroni corrections applied for multiple comparisons.

• Study Type: Interventional
• Enrollment (Actual): 96
• Phase: Not Applicable

Contacts and Locations

Study Locations

• China
  • Hunan
    • Changsha, Hunan, China, 410007
      • The First Affiliated Hospital of Hunan University of Chinese Medicine

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult
• Accepts Healthy Volunteers: Yes

Description

Inclusion Criteria:

• Fifth-year undergraduate dental students undergoing clinical clerkship at the Department of Stomatology, Hunan University of Chinese Medicine.
• Completed all core didactic and theoretical courses in endodontics.
• Entered the early stage of clinical rotation.
• Provided signed voluntary informed consent to participate in the trial.

Exclusion Criteria:

• Prior experience with specialized clinical communication simulation or specialized AI communication training.
• Presence of unavoidable schedule conflicts during the study period.
• Factors affecting student eligibility to complete the full training and evaluation process.

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Other
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: Single

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: Experimental Group; Participants received a 1-month generative AI-based immersive training program using the Gemini platform, engaging in standardized interactive simulations of six high-stakes endodontic clinical scenarios with immediate personalized feedback.	Other: Generative AI-Based Immersive Training; 1-month generative AI-based immersive training program utilizing the Gemini platform. Participants engage in 10-15 minute adaptive conversational simulations every 3-4 days covering six high-stakes endodontic clinical scenarios (such as acute pain management, instrument separation disclosure, and pulp floor perforation), receiving immediate personalized feedback on risk disclosure completeness and empathetic communication.
Active Comparator: Control Group; Participants underwent conventional case-based learning (CBL) targeting the same six endodontic scenarios over 1 month, involving group case discussions, faculty lectures, and standard informed consent reviews.	Other: Conventional Case-Based Learning; 1-month conventional case-based learning curriculum targeting the exact same six high-stakes endodontic clinical scenarios. Learning involves structured case discussions, faculty-led lectures, and review of standardized informed consent templates without adaptive conversational immersion or real-time AI feedback.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Endodontic Risk Disclosure and Informed Consent (RD-IC) Completeness Score	Evaluated via a validated 10-item checklist covering core indications, intraoperative complications, postoperative pain, long-term structural defects, poor prognosis, anatomical variations, sequential treatments, anesthetic allergies, systemic diseases, and poor compliance. Scores range from 0 to 100, with higher scores indicating superior technical accuracy and completeness in risk disclosure.	Immediately post-intervention (T1, at 1 month after study baseline)

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
SEGUE Framework Doctor-Patient Communication Competence Score	Evaluated using the SEGUE framework checklist, assessing 5 communication domains: Set the Stage, Elicit Information, Give Information, Understand Patient Perspective, and End the Encounter. Total median scores range from 0 to 25, with higher scores reflecting superior systematic doctor-patient interaction skills.	Immediately post-intervention (T1, at 1 month after study baseline)
Clinical Communication Self-Efficacy Scale (SCS) Score	Measures students' confidence across 4 domains: Information Gathering, Clinical Information Delivery, Emotional Empathy, and Conflict Management/Closing. Scores range from 20 to 100, with higher scores indicating higher self-efficacy.	Immediately post-intervention (T1, at 1 month after study baseline)
Communication Anxiety Scale (CAS) Score	Evaluates clinical communication anxiety across 4 sub-domains: Situational Tension and Physical Anxiety, Professional Self-Doubt and Worry, Endodontic Risk Disclosure Anxiety, and Communication Burden and Avoidance Tendency. Scores range from 12 to 60, with lower scores indicating reduced clinical communication anxiety.	Immediately post-intervention (T1, at 1 month after study baseline)
Blinded Standardized Patient (SP) Core Clinical Communication Competence Score	External assessment rated by blinded standardized patients across 5 core clinical domains: Reception Etiquette, Standardized Inquiry, Risk Informed Consent Communication, Emotional Empathy, and Closed-loop Guidance. Total scores range from 0 to 100, with higher scores reflecting better clinical communicative performance.	Immediately post-intervention (T1, at 1 month after study baseline)
AI Simulation Teaching Experience Scale Score	Assesses student satisfaction with the educational intervention across 5 sub-scales: Platform Operation, Simulation Scene Authenticity, AI Real-time Feedback Quality, Perceived Ability Improvement, and Recognition of New Teaching Mode. Total scores range from 20 to 100, evaluated against a theoretical neutral midpoint of 50.	Immediately post-intervention (T1, at 1 month after study baseline)
Long-term Retention Score of Endodontic Risk Disclosure (1-Month Follow-Up)	Evaluates retention of communication skills 1 month post-intervention (T2-1m) across 5 sub-items: Basic Disease Communication, Intraoperative Risk Disclosure, Postoperative Risk Communication, Empathetic Alternative Plan Communication, and Closed-loop Consent Procedure. Total scores range from 0 to 100.	1-month post-intervention follow-up (T2-1m, at 2 months after study baseline)
Long-term Retention Score of Endodontic Risk Disclosure (2-Month Follow-Up)	Evaluates long-term durability and resistance to skill decay 2 months post-intervention (T2-2m) across the same 5 risk disclosure sub-items. Total scores range from 0 to 100.	2-month post-intervention follow-up (T2-2m, at 3 months after study baseline)

Collaborators and Investigators

• Sponsor: The First Affiliated Hospital of Hunan University of Traditional Chinese Medicine

Study record dates

Study Major Dates

• Study Start (Actual): March 1, 2026
• Primary Completion (Actual): April 1, 2026
• Study Completion (Actual): May 31, 2026

Study Registration Dates

• First Submitted: July 23, 2026
• First Submitted That Met QC Criteria: July 23, 2026
• First Posted (Actual): July 28, 2026

Study Record Updates

• Last Update Posted (Actual): July 28, 2026
• Last Update Submitted That Met QC Criteria: July 23, 2026
• Last Verified: July 1, 2026

More Information

Terms related to this study

• Keywords: Informed consent; Endodontics; Risk disclosure; Generative artificial intelligence; Immersive simulation
• Other Study ID Numbers: MR-43-26-046512; 2023-JG048 (Other Grant/Funding Number: Teaching Reform Research Project of Hunan University of Traditional Chinese Medicine); 2026-JG060 (Other Grant/Funding Number: 2026 Hunan Provincial Teaching Reform Research Project for General Higher Education)

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: YES
• IPD Plan Description: The de-identified individual participant data collected during the trial will be made available from the corresponding author upon reasonable academic request.
• IPD Sharing Time Frame: Data will be available immediately following publication of the manuscript.
• IPD Sharing Access Criteria: Data will be shared with qualified academic researchers upon reasonable request submitted via email to the corresponding author (libo@hnucm.edu.cn).
• IPD Sharing Supporting Information Type: STUDY_PROTOCOL; SAP; ICF

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No