Multimodal AI for Rhinoplasty Consultation and Simulation: A Blinded Expert Evaluation
Aims and Backgrounds: Multimodal AI can generate rhinoplasty advice and postoperative simulations, but patient-specific validity is uncertain. We assessed expert ratings of clinical content, image quality, coherence, and consultation utility. Technology: GPT-5.5 generated rhinoplasty consultations and simulated postoperative images from preoperative photographs using a standardized patient-voiced prompt. Patient Selection: Preoperative photographs from 20 rhinoplasty patients were retrospectively evaluated. Techniques: Four blinded fellowship-trained facial plastic surgeons rated each output using 12 five-point items, two utility items, and one surgical-plan agreement item. Mixed models included crossed random effects for case and evaluator. Institutional review board approval was obtained. Current and Future Development: = 0.18). Consultation usefulness received unqualified endorsement in 5.0% of assessments and qualified endorsement in 78.8%; full agreement with the plan occurred in 7.6%. Conclusions and Clinical Relevance: Despite clear language and visually plausible simulations, patient-specific clinical validity was inconsistent, supporting supervised adjunctive use only.
Authors
- Grant S. Hamilton (ORCID: https://orcid.org/0000-0001-8445-0575)
- Deanna C. Menapace (ORCID: https://orcid.org/0000-0003-2596-2719)
- Eran Glikson (ORCID: https://orcid.org/0000-0001-8924-9811)
- Matthew Lee (ORCID: https://orcid.org/0000-0002-2842-7191)
- Sholem Hack (ORCID: https://orcid.org/0009-0001-0651-6994)
- Salman Hasan
- Ophir Elizur
- Eli Gordin
- Elia Rosenfeld Elizur
Institutions
- Cedars-Sinai Medical Center (US)
- Mayo Clinic (US)
- Tel Aviv University (IL)
- Sheba Medical Center (IL)
- Mayo Clinic in Florida (US)
- The University of Texas Southwestern Medical Center (US)
- The University of Texas Health Science Center at Houston (US)
Publication Details
- Journal
- Facial Plastic Surgery
- Published
- 2026-11-20
- DOI
- https://doi.org/10.1055/a-3003-2319
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00