Related Experiment Video
Updated: Jun 21, 2026
A Postoperative Evaluation Guideline for Computer-Assisted Reconstruction of the Mandible
Published on: January 28, 2020
Large language model applications in facial plastic and reconstructive surgery: a systematic review of applications,
Bianca-Marina Georgescu1, Antonino Maniaci1,2, Thomas Radulesco3
1Department of Surgery, UMONS Research Institute for Health Sciences and Technology, University of Mons (UMons), Mons, Belgium.
Background:
Artificial intelligence (AI)-powered large language models (LLMs) are increasingly used as adjunctive tools in education, research, and patient care. This systematic review aimed to investigate the current literature on the applications, performance, and ethical considerations regarding the use of artificial intelligence (AI), including large language models (LLM) in plastic and reconstructive surgery.
Methods:
A comprehensive search of PubMed, Scopus, and Cochrane Library was conducted by two independent investigators for studies published in English in peer-reviewed journals reporting findings about applications (education, clinical decision-making, research process), ethical and practical challenges (bias, data privacy, and accountability), and performance of LLMs in facial plastic and reconstructive surgery practice. PRISMA statements and PICOTS frameworks were used for conducting the search and summarizing the literature findings.
Results:
Twenty-one studies met inclusion criteria, including 11 examining practical uses of ChatGPT and other LLMs, 8 evaluating performance on medical and surgical tasks, and 7 assessing ethical issues and potential limitations. Based on several performance tools, LLMs demonstrated moderate-to-high accuracy, ranging from 54.96% to 77.3%, for generating operative notes, improving patient communication, and conducting literature synthesis. The following concerns were identified in the literature: risk of hallucination or misinformation, lack of data protection compliance, and insufficient transparency. More robust evidence-based longitudinal investigations are needed to establish not only safety and effectiveness but also real-world feasibility.
Conclusion:
LLMs report promising application results in plastic and reconstructive surgery, particularly for educational and administrative purposes. The use of LLMs in plastic and reconstructive surgical practice remains limited by the lack of evidence-based longitudinal investigations and unclear data protection and ethical frameworks.
