Identification of Board-Certified Plastic Surgeons Using Artificial Intelligence: An Accuracy Assessment

Artificial intelligence (AI), particularly large language models like ChatGPT (OpenAI, San Francisco, CA) and Gemini (Google, Mountain View, CA), is increasingly used in healthcare for diagnosis, education, and research. Because interest in cosmetic procedures rises, patients face growing difficulty in selecting qualified providers because of unclear credentials and expanding practitioner types.

This study evaluates whether AI can help patients accurately identify board-certified plastic surgeons, addressing a current gap in the literature.

Four leading AI tools-ChatGPT, Perplexity (Perplexity AI, San Francisco, CA), Gemini, and Claude (Anthropic, San Francisco, CA)-were evaluated by asking each to name board-certified plastic surgeons across all 50 US states. Results were verified through independent internet searches and the American Board of Plastic Surgery to confirm certification status. Statistical analysis using GraphPad Prism (Boston, MA) found differences between tools, with significance set at α = .05.

Across 1000 results, overall accuracy in identifying plastic surgeons was 94.1%, with Gemini performing best, followed by Perplexity, ChatGPT, and Claude, with statistically significant differences. Most nonplastic surgeons were otolaryngologists and general surgeons, with no difference between AI models in error type distribution. Gemini scored the highest in regards to board certification accuracy, showing significant differences compared with the other models.

Because the field of aesthetic procedures grows and more providers enter the market, patients must be able to make well-informed choices when selecting a practitioner. Although AI offers a promising tool for identifying board-certified plastic surgeons, its potential for error means patients should independently verify the information.