Artificial intelligence-based chatbot assistance in clinical decision-making for medically complex patients in oral...

Area of Science:

• Oral and Maxillofacial Surgery
• Artificial Intelligence in Healthcare
• Clinical Decision Support Systems

Background:

• Medically complex patients present unique challenges in oral surgery.
• Clinical decision-making requires accurate and timely information.
• AI-based chatbots are emerging as potential tools in healthcare.

Purpose of the Study:

• To evaluate the efficacy of AI chatbots in assisting clinical decision-making for medically complex oral surgery patients.
• To compare the performance of ChatGPT and Claude-instant in providing relevant information.

Main Methods:

• Oral and maxillofacial surgeons developed and validated questions on systemic diseases relevant to oral surgery.
• ChatGPT and Claude-instant were queried with these questions in separate sessions.
• Responses were assessed for quality, accuracy, and completeness by blinded surgeons using modified DISCERN and Likert scales.

Main Results:

• Both chatbots provided high-quality responses (ranging from 79.6% to 89%).
• Accuracy rates were high for both: ChatGPT (92%-93.4%) and Claude-instant (89%-95.2%).
• Completeness scores were also strong: ChatGPT (86.8%-88.5%) and Claude-instant (86%-95.2%).

Conclusions:

• AI chatbots demonstrate significant potential in supporting clinical decisions in oral surgery.
• These tools can offer rapid solutions, potentially easing workload and reducing costs.
• Continued development and acceptance may enhance their role in managing complex patient care.