Back to 2024 Abstracts
Preoperative Patient Guidance & Education In Aesthetic Breast Plastic Surgery: Assessment Of Artificial Intelligence Performance
Jad Abi-Rafeh, MD, MSc1, Brian Bassiri-Tehrani, MD, FACS
2, Heather Furnas, MD, FACS
3, Dennis Hammond, MD, FACS
4, William P. Adams, Jr., MD, FACS
5, Roy Kazan, MD, PhD, FRCSC
1, Foad Nahai, MD, FACS
6;
1McGill University, Montreal, QC, Canada,
2Private Practice, New York, NY, USA,
3Stanford University, Stanford, CA, USA,
4Michigan State University, Michigan, MI, USA,
5University of Texas Southwestern, Dallas, TX, USA,
6Emory University, Atlanta, GA, USA
PURPOSE: At a time when internet and social media use is omnipresent among patients in their self-directed research about their medical or surgical needs, artificial intelligence (AI) large language models are on track to represent hallmark resources in this context. The authors aim to assess AI performance in answering questions posed by simulated patients interested in aesthetic breast plastic surgery.
METHODS: ChatGPT was queried via simulated interactions from the perspective of patients interested in breast augmentation, mastopexy, and breast reduction. Questions posed were standardized and categorized under aesthetic needs inquiries and awareness of appropriate procedures; patient candidacy and indications; procedure safety and risks; procedure information, steps, and techniques; patient assessment; preparation for surgery; post-procedure instructions and recovery; and procedure cost and surgeon recommendations. Using standardized Likert scales, four expert breast plastic surgeons evaluated the AI responses. A post-participation survey assessed expert evaluators’ experience with AI, perceived utility, and limitations.
RESULTS: Overall performance across all question categories, assessment criteria, and procedures examined was 7.3/10±0.5. Overall accuracy of information shared was scored at 7.1/10±0.5; comprehensiveness at 7.0/10±0.6, objectivity at 7.5/10±0.4, safety at 7.5/10±0.4, communication clarity at 7.3/10±0.2, and acknowledgement of limitations at 7.7/10±0.2. With regards to performance on procedures examined, ChatGPT’s overall score was 7.0/10±0.8 for breast augmentation; 7.6/10±0.5 for mastopexy, and 7.4/10±0.5 for breast reduction. Score on breast implant-specific knowledge was 6.7/10±0.6.
CONCLUSION: Albeit not without limitations, ChatGPT represents a promising resource for patient guidance and education. The model’s machine-learning capabilities may explain its improved performance efficiency.
Back to 2024 Abstracts
