Abstract
BACKGROUND: ChatGPT is an open-source artificial large language model that uses deep learning to produce human-like text dialogue. This observational study evaluated the ability of ChatGPT to provide informative and accurate responses to a set of hypothetical questions designed to simulate an initial consultation about rhinoplasty. METHODS: Nine questions were prompted to ChatGPT on rhinoplasty. The questions were sourced from a checklist published by the American Society of Plastic Surgeons, and the responses were assessed for accessibility, informativeness, and accuracy by Specialist Plastic Surgeons with extensive experience in rhinoplasty. RESULTS: ChatGPT was able to provide coherent and easily comprehensible answers to the questions posed, demonstrating its understanding of natural language in a health-specific context. The responses emphasized the importance of an individualized approach, particularly in aesthetic plastic surgery. However, the study also highlighted ChatGPT's limitations in providing more detailed or personalized advice. CONCLUSION: Overall, the results suggest that ChatGPT has the potential to provide valuable information to patients in a medical context, particularly in situations where patients may be hesitant to seek advice from medical professionals or where access to medical advice is limited. However, further research is needed to determine the scope and limitations of AI language models in this domain and to assess the potential benefits and risks associated with their use. LEVEL OF EVIDENCE V: Observational study under respected authorities. This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266 .