Application of ChatGPT in Cosmetic Plastic Surgery: Ally or Antagonist?
Rohun Gupta, Parna Pande, Isabel Herzog, Joseph Weisberger, John Chao, Kongkrit Chaiyasate, Edward S. Lee
Abstract
From the development of life-saving devices to the introduction of electronic health records, technology and artificial intelligence (AI) have had a profound impact on medicine. More recently, OpenAI, a research laboratory based in San Francisco, CA, released a large language model, ChatGPT, to the general public on November 30, 2022. Unlike other large language models, ChatGPT has the ability to process and respond to commands in a humanistic fashion by acknowledging shortcomings and learning from previous mistakes.1 Plastic and reconstructive surgery is a field of innovation, relying on research to improve patient-centered outcomes. Cosmetic surgery, in particular, is an ever-evolving field, with over US$16.7 billion spent on procedures in the United States alone in 2020 according to statistics reported by The Aesthetic Society.2 Systematic reviews are important to the field of plastic surgery, as they serve to deliver a comprehensive depiction of available evidence on a specific topic in the field; furthermore, they help to identify knowledge gaps, address methodology concerns, and answer overarching research questions. Due to the novelty of ChatGPT and the importance of evidence-based research in cosmetic surgery, we wanted to determine whether or not ChatGPT could be utilized to aid in the development of unpublished systematic review topics. In order to incorporate both the broad and the specific aspects of cosmetic plastic surgery, ChatGPT was given 3 commands: “Give me 10 novel systematic review ideas that have not been published in cosmetic plastic surgery” (Table 1; Figure 1). “Give me 5 novel systematic review ideas that have not been published related to rhinoplasty” (Table 2). “Give me 5 novel systematic review ideas that have not been published related to blepharoplasty” (Table 3). Command given to ChatGPT and response provided by ChatGPT. Ten ChatGPT-generated Systematic Review Topics Within General Cosmetic Surgery, Corresponding Number of Nonsystematic and Systematic Reviews Already Published on Topic, and Novelty Status Five ChatGPT-generated Systematic Review Topics Involving Rhinoplasty, Corresponding Number of Nonsystematic and Systematic Reviews Already Published on Topic, and Novelty Status Five ChatGPT-generated Systematic Review Topics Involving Blepharoplasty, Corresponding Number of Nonsystematic and Systematic Reviews Already Published on Topic, and Novelty Status In total, the AI model would devise a total of 20 “unpublished” systematic review ideas within cosmetic surgery. In order to assess the accuracy of ChatGPT, we conducted a literature search in PubMed (National Institutes of Health; Bethesda, MD), CINAHL (EBSCO Information Services; Ipswich, MA), EMBASE (Elsevier; Amsterdam, the Netherlands), and Cochrane (Cochrane Library; London, UK) to account for general literature and the number of systematic reviews that had been published on each topic. Overall, we found that ChatGPT had a 65% accuracy in conceiving innovative systematic review ideas (Table 4). When stratified by general and specific topics within cosmetic surgery, we found that ChatGPT was 50% accurate for general cosmetic surgery and 80% accurate for specific topics (rhinoplasty and blepharoplasty). There were an average of 274.7 nonsystematic reviews and an average of 7.7 systematic reviews that were published for the group of topics that were found to have systematic reviews published. On the other hand, there were an average of 57.8 nonsystematic review articles that were published for the group of ideas that did not have any systematic reviews published. Number of Novel ChatGPT-generated Topics Within Cosmetic Surgery for Their Respective General Category and 2 Subcategories Our findings are not without limitations. Although ChatGPT has been trained on several major datasets, its last data upload was in 2021.3 As a result, there were some systematic reviews that had been published during 2022 and 2023 that were reported to be “novel” by ChatGPT. It is entirely possible that ChatGPT may not be able to present users with the most reliable and up-to-date information. Future updates or installations of ChatGPT may ameliorate this problem. Additionally, our sample size was small, consisting of only 20 “novel” systematic review ideas. However, we did find that the system responds more accurately with specific topics, which was demonstrated by an increase in accuracy from 50% to 80% when assessing general and specific topics within cosmetic plastic surgery. We believe this may be due to ChatGPT responding more accurately when specific questions or commands are given to the software. Further testing of the machine-learning capabilities of the ChatGPT software, in addition to giving more specific instructions, may aid in increasing the accuracy rates of ChatGPT. Although not perfect, ChatGPT has demonstrated itself to be a platform that can be utilized by clinicians to improve the quality of care that is provided to patients. ChatGPT is versatile—it can be used to answer questions, generate content, and perform sentiment analysis. The program is an invaluable tool for clinicians who are looking to supplement their work with efficient, knowledgeable, and constantly evolving AI software. Beyond employing ChatGPT for research purposes, the software can be used for the following purposes: Clinical decision support: assisting healthcare professionals in making informed decisions by providing patients with quick and accurate answers to questions regarding diagnosis, treatment options, and expectations. Virtual health assistance: integration into virtual health platforms to provide patients with immediate assistance in the perioperative period, which could lead to reduced wait times and improved access to care. Although it is entirely possible that users of ChatGPT may utilize the software for personal gain, we believe that ChatGPT has the potential to be used in a manner that is both conducent and respectful to the scientific and medical community, when used by trained plastic surgeons. Our study was an attempt at proof of concept and future studies could explore accuracy rates for other common cosmetic procedures, such as breast augmentation, abdominoplasty, and body contouring. We hope that our brief study provided here will inspire our colleagues inside and outside of plastic surgery to utilize machine learning to ultimately enhance patient outcomes and commit to producing evidence-based research. Although we recognize alternative viewpoints that may be expressed by others in the scientific community, we believe that AI has the potential to enhance the field of medicine. For decades medicine, especially plastic surgery, has utilized technology to our advantage to propel our field forward. We hope that the brief outline provided here will inspire colleagues around the world and guide their investigative efforts to ultimately increase patient safety and obtain individualized and reproducible outcomes. The authors declared no potential conflicts of interest with respect to the research, authorship, and publication of this article. The authors received no financial support for the research, authorship, and publication of this article.