JMIR Publications

ABSTRACT

Background:

Shared decision making (SDM) is a core competency in patient-centered care, yet it is challenging for physicians. Simulation-based education with standardized patients offers valuable practice opportunities for undergraduate medical education (UME), but is limited by cost, scalability, and variable feedback quality. Advances in large language model (LLM) technology and virtual patient (VP) design present a promising pathway toward accessible, realistic, and high-quality SDM skill training.

Objective:

This study aimed to develop LLM-powered, real-time interactive 3D avatars for SDM training in UME, and to evaluate their acceptance among undergraduate medical students.

Methods:

We conducted a descriptive, cross-sectional study at KU Leuven, Belgium (November – December 2025). The avatar system was developed through an iterative, interdisciplinary collaboration, grounded in prior theoretical work. The final system is a web-based platform featuring real-time, LLM-powered spoken dialogue with diverse, photorealistic 3D patient avatars and automated AI-generated feedback. A convenience sample of UME students completed a 9-item, 5-point Likert scale questionnaire grounded in the Technology Acceptance Model after having used the avatar system for one month, assessing perceived usefulness, perceived ease of use, and intention to use. Optional open-text responses were collected and narratively analyzed.

Results:

Of 25 recruited participants, 24 were included in the analysis. Internal consistency was acceptable for perceived usefulness (α=0.76) and intention to use (α=0.78), but not for perceived ease of use (α=0.69). Students rated perceived usefulness highest (mean 4.43, SD 0.50), followed by intention to use (mean 4.42, SD 0.59), and perceived ease of use lowest (mean 3.81, SD 0.68). Qualitative feedback highlighted the value of a safe, low-pressure practice environment, pointed out mixed experiences with perceived avatar realism and identified technical difficulties (microphone issues, system crashes) as area for improvement.

Conclusions:

LLM-powered, real-time interactive 3D avatars are feasible and well-accepted tools for SDM training in UME. Students found the system educationally valuable and expressed strong intention to use it again. Technical reliability and behavioral realism should be prioritized in future development. Larger, multi-institutional studies with objective learning outcome measures are needed to establish efficacy.