Artificial Intelligence Chatbots as Virtual Patients in Dental Education: A Constructivist Approach to Classroom Implementation.

Abstract

Introduction: Advances in artificial intelligence (AI) have led to new possibilities for AI role-play in classroom settings, where generative pre-trained transformers (GPTs) and chatbots can potentially simulate interactions with patients. This pilot study aimed to design an AI role-play activity underpinned by constructivist principles, implement the activity in a classroom setting, and evaluate the students' engagement with the activity and usability of the interface.

Materials and methods: The AI role-play was designed based on a patient presenting to a dental teaching hospital in pain. It comprised two interconnected chatbots intended to simulate a patient consultation and clinical supervisor discussion. The chatbots were built using the open-source framework Streamlit and powered by Chat GPT-4. Second and final-year students from an oral health degree were recruited through convenience sampling. Classroom observations were recorded and final-year students participated in a usability questionnaire to gain insights into their engagement, technical challenges, and suggestions for improvement. Data usage and token costs were collected to assess the AI chatbot's feasibility.

Results: Educator observations noted that AI role-play facilitated peer discussion, highlighted gaps in history-taking, and promoted peer learning. Usability survey feedback (n = 14) suggested that students perceived the AI role-play as authentic and relevant to clinical practice, with 86% strongly agreeing it aligned with real-world dental scenarios. The screen design, navigation, and multimedia integration were highly rated. The approximate costs for the activities were $13.17 (USD) for approximately 20 queries, per 20 students.

Conclusion: This study presents a descriptive analysis of the implementation of an AI role-play within the early phases of a design-based research framework. AI role-play activities can be implemented in a classroom setting and are perceived as useful for students to apply skills in taking a pain history. While results showed promise for scalability and authentic learning, future research evaluating the impact of the implementation of these activities on student learning should be explored.