Introduction: Large language models, such as ChatGPT, hold tremendous promise to bridge gaps in patient education and enhance the decision-making resources available online for patients seeking nasal surgery.Objective: To compare the performance of ChatGPT in answering preoperative and postoperative patient questions related to septorhinoplasty.Methods: Two sets of responses were collected for the questions: one from an expert rhinoplasty surgeon with over two decades of experience, and the other from ChatGPT-3.5. Seven expert rhinoplasty surgeons, blinded to the source of responses, independently assessed the responses using a 5-point Likert scale in four performance areas: empathy, accuracy, completeness, and overall quality.Results: ChatGPT outperformed physician responses in three of the four performance areas, earning significantly higher ratings in accuracy, completeness, and overall quality (p < 0.001). In addition, ChatGPT was overwhelmingly preferred over physician responses (p < 0.001), with evaluators favoring ChatGPT in 80.95% of instances.Conclusions: ChatGPT has demonstrated its remarkable ability to deliver accurate, complete, and high-quality responses to preoperative and postoperative patient questions. Although certain improvements are warranted, this artificial intelligence tool has shown its potential to effectively counsel and educate prospective septorhinoplasty patients at a level comparable with or exceeding that of an expert surgeon.

Artificial Intelligence Versus Expert Plastic Surgeon: Comparative Study Shows ChatGPT “Wins” Rhinoplasty Consultations: Should We Be Worried?

Bertossi, Dario;
2023-01-01

Abstract

Introduction: Large language models, such as ChatGPT, hold tremendous promise to bridge gaps in patient education and enhance the decision-making resources available online for patients seeking nasal surgery.Objective: To compare the performance of ChatGPT in answering preoperative and postoperative patient questions related to septorhinoplasty.Methods: Two sets of responses were collected for the questions: one from an expert rhinoplasty surgeon with over two decades of experience, and the other from ChatGPT-3.5. Seven expert rhinoplasty surgeons, blinded to the source of responses, independently assessed the responses using a 5-point Likert scale in four performance areas: empathy, accuracy, completeness, and overall quality.Results: ChatGPT outperformed physician responses in three of the four performance areas, earning significantly higher ratings in accuracy, completeness, and overall quality (p < 0.001). In addition, ChatGPT was overwhelmingly preferred over physician responses (p < 0.001), with evaluators favoring ChatGPT in 80.95% of instances.Conclusions: ChatGPT has demonstrated its remarkable ability to deliver accurate, complete, and high-quality responses to preoperative and postoperative patient questions. Although certain improvements are warranted, this artificial intelligence tool has shown its potential to effectively counsel and educate prospective septorhinoplasty patients at a level comparable with or exceeding that of an expert surgeon.
2023
N.A.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11562/1125396
Citazioni
  • ???jsp.display-item.citation.pmc??? 0
  • Scopus 8
  • ???jsp.display-item.citation.isi??? 5
social impact