AI outperforms expert plastic surgeon in rhinoplasty consultations

In a new study, artificial intelligence in the form of ChatGPT outperformed an expert rhinoplasty surgeon in answering preoperative and postoperative patient questions related to nasal surgery. ChatGPT earned significantly higher ratings in accuracy, completeness, and overall quality, according to the study published in Facial Plastic Surgery & Aesthetic Medicine.

Kay Durairaj, MD, and Omer Baker, from Pasadena, California;, Dario Bertossi, MD, from University of Verona; Steven Dayan, MD, from University of Illinois, Chicago; Kian Karimi, MD, from Los Angeles California; Roy Kim, MD, from San Francisco, California; Sam Most, MD, from Stanford University; Enrico Robotti, MD, from Bergamo Italy; and Frand Rosengaus, MD, from Mexico City, reported that ChatGPT was overwhelmingly preferred over physician responses, with evaluators favoring ChatGPT in 80.95% of instances. Their findings are presented in the article titled "Artificial Intelligence Versus Expert Plastic Surgeon: Comparative Study Shows ChatGPT 'Wins' Rhinoplasty Consultations: Should We Be Worried?"

"Our findings showed that ChatGPT displayed a remarkable ability to effectively respond to a wide breadth of patient questions, encompassing optics such as nonsurgical treatment options and postoperative care instructions," stated the investigators. "In the majority of instances, ChatGPT performed at or above the level of an expert rhinoplasty surgeon."

Facial Plastic Surgery & Aesthetic Medicine Editor-in-Chief Travis T. Tollefson, MD, MPH, University of California, Davis, states, "Online tools such as ChatGPT are making Artificial Intelligence (AI) or large language models (LLM) accessible to the public with so much excitement. To best serve our patients and the overall medical community, we must remain conscientious to the appropriate use of these technologies.

"It is astounding to read AI-generated content that has been edited in the writing style of Hemingway or Dostoevsky. It remains our responsibility to counsel patients on the occasional inaccurate statements made in AI-generated content. We can both acknowledge that most of our patients will be using AI and focus our efforts on maintaining the integrity of our patient education and consultation practices."