Answers are grounded in this paper and cite their sources.
Objective This study developed an AI-powered chatbot simulating a patient with acute pulpitis to enhance history-taking training in stomatology, aiming at providing a cost-effective tool that improves diagnostic and communication skills while fostering clinical competence and empathy. Methods The study involved 126 undergraduate clinical medicine students who interacted with an AI agent simulating a patient suffering acute pulpitis. The AI agent was created and optimized in a five-step process, including preliminary creation, usability testing with a Chatbot Usability Questionnaire (CUQ), analysis and optimization, retesting, and comparison of pre- and post-optimization results. The platform used was ChatGLM, and statistical analysis was performed using R software. Results The pre-optimization group’s CUQ mean score was 64.2, indicating moderate satisfaction. After optimization, the post-optimization group’s mean score improved to 79.3, showing significantly higher satisfaction. Improvements were noted in all aspects, particularly in the chatbot’s personality, user experience, error handling, and onboarding. Conclusion The optimized AI agent effectively addresses challenges in history-taking training, improving realism, engagement, and accessibility to diverse scenarios. It demonstrates the potential of AI-powered chatbots as valuable tools for enhancing medical education.
No takes yet. Share an insight, caveat, or question.
Yuan et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: