Saved in:
Bibliographic Details
Main Authors: Amithasagaran, Akilan, Dakshit, Sagnik, Suryadevara, Bhavani, Stockton, Lindsey
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.19031
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914107579432960
author Amithasagaran, Akilan
Dakshit, Sagnik
Suryadevara, Bhavani
Stockton, Lindsey
author_facet Amithasagaran, Akilan
Dakshit, Sagnik
Suryadevara, Bhavani
Stockton, Lindsey
contents Simulations constitute a fundamental component of medical and nursing education and traditionally employ standardized patients (SP) and high-fidelity manikins to develop clinical reasoning and communication skills. However, these methods require substantial resources, limiting accessibility and scalability. In this study, we introduce CLiVR, a Conversational Learning system in Virtual Reality that integrates large language models (LLMs), speech processing, and 3D avatars to simulate realistic doctor-patient interactions. Developed in Unity and deployed on the Meta Quest 3 platform, CLiVR enables trainees to engage in natural dialogue with virtual patients. Each simulation is dynamically generated from a syndrome-symptom database and enhanced with sentiment analysis to provide feedback on communication tone. Through an expert user study involving medical school faculty (n=13), we assessed usability, realism, and perceived educational impact. Results demonstrated strong user acceptance, high confidence in educational potential, and valuable feedback for improvement. CLiVR offers a scalable, immersive supplement to SP-based training.
format Preprint
id arxiv_https___arxiv_org_abs_2510_19031
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CLiVR: Conversational Learning System in Virtual Reality with AI-Powered Patients
Amithasagaran, Akilan
Dakshit, Sagnik
Suryadevara, Bhavani
Stockton, Lindsey
Human-Computer Interaction
Artificial Intelligence
Computers and Society
Simulations constitute a fundamental component of medical and nursing education and traditionally employ standardized patients (SP) and high-fidelity manikins to develop clinical reasoning and communication skills. However, these methods require substantial resources, limiting accessibility and scalability. In this study, we introduce CLiVR, a Conversational Learning system in Virtual Reality that integrates large language models (LLMs), speech processing, and 3D avatars to simulate realistic doctor-patient interactions. Developed in Unity and deployed on the Meta Quest 3 platform, CLiVR enables trainees to engage in natural dialogue with virtual patients. Each simulation is dynamically generated from a syndrome-symptom database and enhanced with sentiment analysis to provide feedback on communication tone. Through an expert user study involving medical school faculty (n=13), we assessed usability, realism, and perceived educational impact. Results demonstrated strong user acceptance, high confidence in educational potential, and valuable feedback for improvement. CLiVR offers a scalable, immersive supplement to SP-based training.
title CLiVR: Conversational Learning System in Virtual Reality with AI-Powered Patients
topic Human-Computer Interaction
Artificial Intelligence
Computers and Society
url https://arxiv.org/abs/2510.19031