Ophthalmic Plast Reconstr Surg. 2023 Dec 19. doi: 10.1097/IOP.0000000000002574. Online ahead of print.
ABSTRACT
PURPOSE: This study aimed to demonstrate the performance of the popular artificial intelligence (AI) language model, Chat Generative Pre-trained Transformer (ChatGPT) (OpenAI, San Francisco, CA, U.S.A.), in generating the informed consent (IC) document of blepharoplasty.
METHODS: A total of 2 prompts were provided to ChatGPT to generate IC documents. Four board-certified plastic surgeons and 4 nonmedical staff members evaluated the AI-generated IC documents and the original IC document currently used in the clinical setting. They assessed these documents in terms of accuracy, informativeness, and accessibility.
RESULTS: Among board-certified plastic surgeons, the initial AI-generated IC document scored significantly lower than the original IC document in accuracy (p < 0.001), informativeness (p = 0.005), and accessibility (p = 0.021), while the revised AI-generated IC document scored lower compared with the original document in accuracy (p = 0.03) and accessibility (p = 0.021). Among nonmedical staff members, no statistical significance of 2 AI-generated IC documents was observed compared with the original document in terms of accuracy, informativeness, and accessibility.
CONCLUSIONS: Our results showed that current ChatGPT cannot be used as a distinct patient education resource. However, it has the potential to make better IC documents when improving the professional terminology. This AI technology will eventually transform ophthalmic plastic surgery healthcare systematics by enhancing patient education and decision-making via IC documents.
PMID:38133626 | DOI:10.1097/IOP.0000000000002574
