Comparative Analysis of Artificial Intelligence Responses to Questions on Plastic Surgery Education: An Exploratory Study
Background: The training of plastic surgery residents is constantly evolving. This study explored whether different artificial intelligence (AI) systems highlight the same key aspects of residency training as experts in the field. Methods: Six modern AI systems (ChatGPT 3.5, ChatGPT 4o, Claude 3.5, Gemini 1.5 Pro, Llama 3.1 70B, and OpenAI o1) were tested on various aspects of residency training. Their responses were evaluated for accuracy, quality, and comprehensiveness both by the AI systems and by field experts. Results: All AI systems delivered accurate and comprehensive responses. OpenAI o1 and ChatGPT 4o consistently ranked highest, nearly achieving excellent scores in all categories. Although some systems addressed certain aspects more superficially, all identified most of the key elements and provided a solid overview of important topics in residency training. Conclusions: OpenAI o1 and ChatGPT 4o stood out for their accuracy and depth, emphasizing the potential of AI in medical education. AI may offer new opportunities for personalized and efficient surgical training.
Paper
Full text
Comparative Analysis of Artificial Intelligence Responses to Questions on Plastic Surgery Education: An Exploratory Study
OpenAlex · Artificial Intelligence in Healthcare and Education · 2026
Abstract
Background: The training of plastic surgery residents is constantly evolving. This study explored whether different artificial intelligence (AI) systems highlight the same key aspects of residency training as experts in the field. Methods: Six modern AI systems (ChatGPT 3.5, ChatGPT 4o, Claude 3.5, Gemini 1.5 Pro, Llama 3.1 70B, and OpenAI o1) were tested on various aspects of residency training. Their responses were evaluated for accuracy, quality, and comprehensiveness both by the AI systems and by field experts. Results: All AI systems delivered accurate and comprehensive responses. OpenAI o1 and ChatGPT 4o consistently ranked highest, nearly achieving excellent scores in all categories. Although some systems addressed certain aspects more superficially, all identified most of the key elements and provided a solid overview of important topics in residency training. Conclusions: OpenAI o1 and ChatGPT 4o stood out for their accuracy and depth, emphasizing the potential of AI in medical education. AI may offer new opportunities for personalized and efficient surgical training.