Large Language Models for Intraoperative Decision Support in Plastic Surgery: A Comparison between ChatGPT-4 and Gemini.

Background and Objectives: Large language models (LLMs) are emerging as valuable tools in plastic surgery, potentially reducing surgeons' cognitive loads and improving patients' outcomes. This study aimed to assess and compare the current state of the two most common and readily available LLMs, Open AI's ChatGPT-4 and Google's Gemini Pro (1.0 Pro), in providing intraoperative decision support in plastic and reconstructive surgery procedures. Materials and Methods: We presented each LLM with 32 independent intraoperative scenarios spanning 5 procedures. We utilized a 5-point and a 3-point Likert scale for medical accuracy and relevance, respectively. We determined the readability of the responses using the Flesch-Kincaid Grade Level (FKGL) and Flesch Reading Ease (FRE) score. Additionally, we measured the models' response time. We compared the performance using the Mann-Whitney U test and Student's t-test. Results: ChatGPT-4 significantly outperformed Gemini in providing accurate (3.59 ± 0.84 vs. 3.13 ± 0.83, p-value = 0.022) and relevant (2.28 ± 0.77 vs. 1.88 ± 0.83, p-value = 0.032) responses. Alternatively, Gemini provided more concise and readable responses, with an average FKGL (12.80 ± 1.56) significantly lower than ChatGPT-4's (15.00 ± 1.89) (p < 0.0001). However, there was no difference in the FRE scores (p = 0.174). Moreover, Gemini's average response time was significantly faster (8.15 ± 1.42 s) than ChatGPT'-4's (13.70 ± 2.87 s) (p < 0.0001). Conclusions: Although ChatGPT-4 provided more accurate and relevant responses, both models demonstrated potential as intraoperative tools. Nevertheless, their performance inconsistency across the different procedures underscores the need for further training and optimization to ensure their reliability as intraoperative decision-support tools.

Trends in Gender Authorship of Abstract Presentations at Plastic Surgery the Meeting: A Decade Long Analysis.

ABSTRACT: Current literature fails to examine gender differences of authors presenting abstracts at national plastic surgery meetings. This study aims to assess the ratio of female to male abstract presentations at Plastic Surgery The Meeting (PSTM).The gender of all abstract presenters from PSTM between 2010 and 2020 was recorded. The primary outcome variable was authorship (first, second, or last). Trends in gender authorship were assessed via Cochran-Armitage trend tests. Chi-square was utilized to evaluate the association between author gender and presentation type and author gender and subspecialty.Between 2010 and 2020, 3653 abstracts were presented (oral = 3035, 83.1%; poster = 618, 16.9%) with 19,328 (5175 females, 26.8%) authors. Of these, 34.5%, 32.0%, and 18.6% of first, second, and last authors were female, respectively. The total proportion of female authors increased from 153 (20.4%) in 2010 to 1065 (33.1%) by 2020. The proportion of female first, second, and last authors increased from 21.8% to 44.8%, 24.0% to 45.3%, and 14.3% to 22.1%, respectively, and demonstrated a positive linear trend ( P < 0.001 ). The proportion of female first authors in aesthetics (23.9%) was lower than that for breast (41.8%), cranio/maxillofacial/head & neck (38.5%), practice management (43.3%), and research/technology (39.4%) ( P < 0.001 ).Our study demonstrates a significant increase in female representation as first, second, and last authors in abstract presentations at PSTM within the last decade, although the absolute prevalence remains low.

Improving Readability and Automating Content Analysis of Plastic Surgery Webpages With ChatGPT.

INTRODUCTION: The quality and readability of online health information are sometimes suboptimal, reducing their usefulness to patients. Manual evaluation of online medical information is time-consuming and error-prone. This study automates content analysis and readability improvement of private-practice plastic surgery webpages using ChatGPT. METHODS: The first 70 Google search results of "breast implant size factors" and "breast implant size decision" were screened. ChatGPT 3.5 and 4.0 were utilized with two prompts (1: general, 2: specific) to automate content analysis and rewrite webpages with improved readability. ChatGPT content analysis outputs were classified as hallucination (false positive), accurate (true positive or true negative), or omission (false negative) using human-rated scores as a benchmark. Six readability metric scores of original and revised webpage texts were compared. RESULTS: Seventy-five webpages were included. Significant improvements were achieved from baseline in six readability metric scores using a specific-instruction prompt with ChatGPT 3.5 (all P ≤ 0.05). No further improvements in readability scores were achieved with ChatGPT 4.0. Rates of hallucination, accuracy, and omission in ChatGPT content scoring varied widely between decision-making factors. Compared to ChatGPT 3.5, average accuracy rates increased while omission rates decreased with ChatGPT 4.0 content analysis output. CONCLUSIONS: ChatGPT offers an innovative approach to enhancing the quality of online medical information and expanding the capabilities of plastic surgery research and practice. Automation of content analysis is limited by ChatGPT 3.5's high omission rates and ChatGPT 4.0's high hallucination rates. Our results also underscore the importance of iterative prompt design to optimize ChatGPT performance in research tasks.

Current trends in retraction of plastic surgery and reconstruction research.

BACKGROUND: Various studies regarding retractions of publications have determined the rate of retraction has increased in recent years. Although this trend may apply to any field, there is a paucity of literature exploring the publication of erroneous studies within plastic and reconstructive surgery. The present study aims to identify trends in frequency and reasons for retraction of plastic and reconstructive surgery studies, with analysis of subspecialty and journals. METHODS: A database search was conducted for retracted papers within plastic and reconstructive surgery. The initial search yielded 2347 results, which were analyzed by two independent reviewers. 77 studies were jointly identified for data collection. RESULTS: The most common reasons for retractions were duplication (n = 20, 25.9 %), request of author (n = 15, 19.5 %), plagiarism (n = 9, 11.6 %), error (n = 9, 11.6 %), fraud (n = 2, 2.6 %), and conflict of interest (n = 1, 1.3 %). 15 were basic science studies (19.4 %), 58 were clinical science studies (75.3 %), and 4 were not categorized (5.2 %). Subspecialties of retracted papers were maxillofacial (n = 29, 37.7 %), reconstructive (n = 17, 22.0 %), wound healing (n = 8, 10.4 %), burn (n = 6, 7.8 %), esthetics (n = 5, 6.5 %), breast (n = 3, 3.9 %), and trauma (n = 1, 1.3 %). Mean impact factor was 2.9 and average time from publication to retraction was 32 months. CONCLUSION: Analysis of retracted plastic surgery studies revealed a recent rise in frequency of retractions, spanning a wide spectrum of journals and subspecialties.

Predictors of Plastic Surgery Applicant Success: An Analysis of the Texas STAR Database.

INTRODUCTION: Integrated plastic surgery residency is one of the most competitive medical specialties. Although previous studies have surveyed integrated plastic surgery residency program directors regarding desired applicant characteristics, there is a paucity of literature assessing detailed application characteristics and reported match outcomes from applicants in recent application cycles. This study examines application characteristics associated with matching into integrated plastic surgery residency from 2017 to 2023. METHODS: The authors accessed the Texas Seeking Transparency in Application to Residency database, which contains survey information from graduating medical students nationwide regarding residency application characteristics and specialties/programs to which applications were submitted. Characteristics of matched versus unmatched applicants between 2017 and 2023 were compared using χ 2 and 2-sided, independent t tests. Univariate logistic regression models were used to assess predictors of a successful match. RESULTS: A total of 381 integrated plastic surgery residency applicants responded to the Texas Seeking Transparency in Application to Residency survey from 2017 to 2023. Mean United States Medical Licensing Exam Step 2 CK scores; the number of away rotations, interview offers, and honored clerkships; and Alpha Omega Alpha membership rate were significantly associated with and predictive of matching. Preference signaling of programs was associated with an increased interview offer rate. CONCLUSIONS: Higher board examination scores, increasing numbers of honored clerkships, away rotations, and Alpha Omega Alpha membership were identified as statistically significant predictors of matching into integrated plastic surgery residency. Prospective applicants should use this information to help guide their efforts in these areas that appear to be associated with a successful transition to residency.

Trends in American Plastic Surgery Procedures (2005-2019): Observing the Growth Rate of Maxillofacial Surgery and Cosmetic Minimally Invasive Procedures in ASPS Data.

BACKGROUND: This study explores the dynamic changes in plastic surgery practices, focusing on the growth rates across different subcategories, particularly highlighting the trends in the United States. OBJECTIVES: To analyze evolving trends in plastic surgery using statistical methods, providing insights into the changes and growth patterns in various segments over time. MATERIALS AND METHODS: Utilizing data from 2005 to 2019 from the American Society of Plastic Surgeons, the authors, conducted a comprehensive statistical analysis using the SPSS program to investigate trends in plastic surgery procedures. RESULTS: Our analysis revealed no significant differences in year-on-year growth rates between cosmetic and reconstructive surgery. However, in reconstructive surgery subcategories, maxillofacial surgery showed the highest mean growth rate at 11.61%, though this was not statistically significant. In cosmetic minimally invasive procedures, soft tissue filler injections and botulinum toxin A injections experienced notably higher growth trends compared with microdermabrasion. CONCLUSION: The findings suggest that practitioners considering a career in plastic surgery should not focus solely on choosing between reconstructive and cosmetic surgery. Recognizing substantial growth in cosmetic minimally invasive procedures, especially botulinum toxin A injections and fillers, is vital for making informed career decisions.