Applying Artificial Intelligence to Facial Feminization Surgery: Understanding of Facial Anatomy,Surgical Techniques,and Patient Education

Abstract

Background:

Artificial intelligence (AI) and machine-learning technology are on the rise, including ChatGPT and Google’s Gemini, previously known as Bard. While recent studies have begun to explore the role of AI in medicine, there are no studies to date on the application of large language models to facial feminization surgery.

Objective:

Establish the reliability of ChatGPT and Google AI (Bard) in providing patient education and describing surgical techniques specific to facial feminization surgery.

Methods:

This was a prospective observational study. Both ChatGPT and Bard were queried with 9 questions. The same series of questions was asked 3 months later. Five expert reviewers were asked to rate responses in a blinded fashion using the modified AI-DISCERN criteria. One-way ANOVA and Tukey’s HSD were used for analysis.

Results:

ChatGPT outperformed Google Bard in areas of harmlessness, truthfulness, relevance, bias, sources, and aims at baseline. However, Bard was often able to resolve this discrepancy in 3 months.

Conclusions:

While large language models show promise in disseminating patient education and general information on facial feminization, caution must be exercised reviewing outputs as inaccurate medical content may be encountered. However, repeated exposure seems to improve the quality of responses over time.