Using artificial intelligence chatbots to improve patient history taking in dental education (Pilot study)

Abstract

In all health professions, taking a patient history is critical to accurate diagnosis and the formulation of an appropriate patient-focused management plan.1 Misdiagnosis and inappropriate treatment are common sequelae when clinicians fail to work through history in a logical and thorough manner. Traditionally, history taking in dentistry is taught in a clinical setting with some opportunities to practice in a simulated environment prior to students entering treatment clinics. Pre-clinical teaching is currently done in a tutorial setting where a clinical educator acts as a patient and the students act as the dentist. Such simulations allow repetitive practice in different clinical situations, within a risk-free environment.2 However, interviews with dental school staff members and observation of these tutorials revealed that in most classes, only one or two students actively participated in this role-playing. ChatGPT is a publicly available artificial intelligence (AI) large language model from OpenAI.3 It receives natural language inputs and responds realistically based on the conversation context. AI can be used to develop educational chatbots that are affordable and can provide a new medium of simulation with more scalability, personalization, and access.4 Research studies have demonstrated the effectiveness of ChatGPT in improving diagnostic accuracy, clinical judgment, and knowledge retention among healthcare learners.4 The use of an AI-generated chatbot is proposed as a solution to these problems by requiring individual interaction with the chatbot prior to clinical training. An educational chatbot was developed and trialed in a group of third-year Doctor of Dental Medicine students. A history-taking chatbot was developed with the student user/“clinician” taking a history from the chatbot/“patient” Students could interact either verbally or by typing. The chatbot was hosted on Vercel, using the Next.js framework for the front end and utilizing Vercel's native serverless functions for access to OpenAI's Application Programming Interface at the backend (Figure 1). The chatbot employs the GPT-3.5 Instruct model with structured chat prompts based on an ideal script to guide patient-practitioner dialogue. A small illustrative section is shown in Figure 2. The use of generative AI allows the chatbot to understand variably expressed questions and respond as realistically as possible. Observation of the tutorial with the clinical educator acting as the patient found only two of 13 students actively participated by asking questions compared with 100% involvement with the chatbot. Students generally found the chatbot useful and perceived competence was improved following chatbot use (Figure 3). Most students also agreed that they participated more with the chatbot and that the chatbot would provide more opportunities for them to practice. Staff also recognized the versatility of the tool and AI's potential to generate more cases, although cautious of the current fallibility of generative accuracy. There is clear potential for educational chatbots in dental education which were well-received by staff and senior students. Future directions include development with GPT-4 and updated AI models, trialing with early-year dental students, and iterations of more cases. This study was supported by the FMH Media lab at The University of Sydney. Open access publishing facilitated by The University of Sydney, as part of the Wiley - The University of Sydney agreement via the Council of Australian University Librarians.

Ähnliche Arbeiten