Artificial Intelligence-Enabled Simulation of Gluteal Augmentation: A Helpful Tool in Preoperative Outcome Simulation?

Unveiling the Potential of AI in Plastic Surgery Education: A Comparative Study of Leading AI Platforms' Performance on In-training Examinations

Background

Within the last few years, artificial intelligence (AI) chatbots have sparked fascination for their potential as an educational tool. Although it has been documented that one such chatbot, ChatGPT, is capable of performing at a moderate level on plastic surgery examinations and has the capacity to become a beneficial educational tool, the potential of other chatbots remains unexplored.

Methods

To investigate the efficacy of AI chatbots in plastic surgery education, performance on the 2019-2023 Plastic Surgery In-service Training Examination (PSITE) was compared among seven popular AI platforms: ChatGPT-3.5, ChatGPT-4.0, Google Bard, Google PaLM, Microsoft Bing AI, Claude, and My AI by Snapchat. Answers were evaluated for accuracy and incorrect responses were characterized by question category and error type.

Results

ChatGPT-4.0 outperformed the other platforms, reaching accuracy rates up to 79%. On the 2023 PSITE, ChatGPT-4.0 ranked in the 95th percentile of first-year residents; however, relative performance worsened when compared with upper-level residents, with the platform ranking in the 12th percentile of sixth-year residents. The performance among other chatbots was comparable, with their average PSITE score (2019-2023) ranging from 48.6% to 57.0%.

Conclusions

Results of our study indicate that ChatGPT-4.0 has potential as an educational tool in the field of plastic surgery; however, given their poor performance on the PSITE, the use of other chatbots should be cautioned against at this time. To our knowledge, this is the first article comparing the performance of multiple AI chatbots within the realm of plastic surgery education.

Sailing the Seven Seas: A Multinational Comparison of ChatGPT's Performance on Medical Licensing Examinations

PURPOSE

The use of AI-powered technology, particularly OpenAI's ChatGPT, holds significant potential to reshape healthcare and medical education. Despite existing studies on the performance of ChatGPT in medical licensing examinations across different nations, a comprehensive, multinational analysis using rigorous methodology is currently lacking. Our study sought to address this gap by evaluating the performance of ChatGPT on six different national medical licensing exams and investigating the relationship between test question length and ChatGPT's accuracy.

METHODS

We manually inputted a total of 1,800 test questions (300 each from US, Italian, French, Spanish, UK, and Indian medical licensing examination) into ChatGPT, and recorded the accuracy of its responses.

RESULTS

We found significant variance in ChatGPT's test accuracy across different countries, with the highest accuracy seen in the Italian examination (73% correct answers) and the lowest in the French examination (22% correct answers). Interestingly, question length correlated with ChatGPT's performance in the Italian and French state examinations only. In addition, the study revealed that questions requiring multiple correct answers, as seen in the French examination, posed a greater challenge to ChatGPT.

CONCLUSION

Our findings underscore the need for future research to further delineate ChatGPT's strengths and limitations in medical test-taking across additional countries and to develop guidelines to prevent AI-assisted cheating in medical examinations.

Turn Your Vision into Reality-AI-Powered Pre-operative Outcome Simulation in Rhinoplasty Surgery

BACKGROUND

The increasing demand and changing trends in rhinoplasty surgery emphasize the need for effective doctor-patient communication, for which Artificial Intelligence (AI) could be a valuable tool in managing patient expectations during pre-operative consultations.

OBJECTIVE

To develop an AI-based model to simulate realistic postoperative rhinoplasty outcomes.

METHODS

We trained a Generative Adversarial Network (GAN) using 3,030 rhinoplasty patients' pre- and postoperative images. One-hundred-one study participants were presented with 30 pre-rhinoplasty patient photographs followed by an image set consisting of the real postoperative versus the GAN-generated image and asked to identify the GAN-generated image.

RESULTS

The study sample (48 males, 53 females, mean age of 31.6 ± 9.0 years) correctly identified the GAN-generated images with an accuracy of 52.5 ± 14.3%. Male study participants were more likely to identify the AI-generated images compared with female study participants (55.4% versus 49.6%; p = 0.042).

CONCLUSION

We presented a GAN-based simulator for rhinoplasty outcomes which used pre-operative patient images to predict accurate representations that were not perceived as different from real postoperative outcomes.

LEVEL OF EVIDENCE III

This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266 .

Truth Lies in the Depths: Novel Insights into Facial Aesthetic Measurements from a U.S. Survey Panel

BACKGROUND

Aesthetic facial bone surgery and facial implantology expand the boundaries of conventional facial surgery that focus on facial soft tissue. This study aimed to reveal novel aesthetic facial measurements to provide tailored treatment concepts and advance patient care.

METHODS

A total of n=101 study participants (46 females and 55 males) were presented with 120 patient portraits (frontal images in natural head posture; 60 females and 60 males) and asked to assess the facial attractiveness (scale 0-10; "How attractive do you find the person in the image?") and the model capability score (MCS; scale 0-10; "How likely do you think the person in the image could pursue a modelling career?"). For each frontal photograph, defined facial measurements and ratios were taken to analyse their relationship with the perception of facial attractiveness and MCS.

RESULTS

The overall attractiveness rating was 4.3 ± 1.1, while the mean MCS was 3.4 ± 1.1. In young males, there was a significant correlation between attractiveness and the zygoma-mandible angle (ZMA)2 (r= - 0.553; p= 0.011). In young and middle-aged females, MCS was significantly correlated with facial width (FW)1-FW2 ratio (r= 0.475; p= 0.034). For all male individuals, a ZMA1 value of 171.79 degrees (Y= 0.313; p= 0.024) was the most robust cut-off to determine facial attractiveness. The majority of human evaluators (n=62; 51.7%) considered facial implants a potential treatment to improve the patient's facial attractiveness.

CONCLUSION

This study introduced novel metrics of facial attractiveness, focusing on the facial skeleton. Our findings emphasized the significance of zygomatic measurements and mandibular projections for facial aesthetics, with FI representing a promising surgical approach to optimize facial aesthetics.

LEVEL OF EVIDENCE IV

This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266 .

Pure Wisdom or Potemkin Villages? A Comparison of ChatGPT 3.5 and ChatGPT 4 on USMLE Step 3 Style Questions: Quantitative Analysis

BACKGROUND

The United States Medical Licensing Examination (USMLE) has been critical in medical education since 1992, testing various aspects of a medical student's knowledge and skills through different steps, based on their training level. Artificial intelligence (AI) tools, including chatbots like ChatGPT, are emerging technologies with potential applications in medicine. However, comprehensive studies analyzing ChatGPT's performance on USMLE Step 3 in large-scale scenarios and comparing different versions of ChatGPT are limited.

OBJECTIVE

This paper aimed to analyze ChatGPT's performance on USMLE Step 3 practice test questions to better elucidate the strengths and weaknesses of AI use in medical education and deduce evidence-based strategies to counteract AI cheating.

METHODS

A total of 2069 USMLE Step 3 practice questions were extracted from the AMBOSS study platform. After including 229 image-based questions, a total of 1840 text-based questions were further categorized and entered into ChatGPT 3.5, while a subset of 229 questions were entered into ChatGPT 4. Responses were recorded, and the accuracy of ChatGPT answers as well as its performance in different test question categories and for different difficulty levels were compared between both versions.

RESULTS

Overall, ChatGPT 4 demonstrated a statistically significant superior performance compared to ChatGPT 3.5, achieving an accuracy of 84.7% (194/229) and 56.9% (1047/1840), respectively. A noteworthy correlation was observed between the length of test questions and the performance of ChatGPT 3.5 (ρ=-0.069; P=.003), which was absent in ChatGPT 4 (P=.87). Additionally, the difficulty of test questions, as categorized by AMBOSS hammer ratings, showed a statistically significant correlation with performance for both ChatGPT versions, with ρ=-0.289 for ChatGPT 3.5 and ρ=-0.344 for ChatGPT 4. ChatGPT 4 surpassed ChatGPT 3.5 in all levels of test question difficulty, except for the 2 highest difficulty tiers (4 and 5 hammers), where statistical significance was not reached.

CONCLUSIONS

In this study, ChatGPT 4 demonstrated remarkable proficiency in taking the USMLE Step 3, with an accuracy rate of 84.7% (194/229), outshining ChatGPT 3.5 with an accuracy rate of 56.9% (1047/1840). Although ChatGPT 4 performed exceptionally, it encountered difficulties in questions requiring the application of theoretical concepts, particularly in cardiology and neurology. These insights are pivotal for the development of examination strategies that are resilient to AI and underline the promising role of AI in the realm of medical education and diagnostics.

Diagnosing lagophthalmos using artificial intelligence

Lagophthalmos is the incomplete closure of the eyelids posing the risk of corneal ulceration and blindness. Lagophthalmos is a common symptom of various pathologies. We aimed to program a convolutional neural network to automatize lagophthalmos diagnosis. From June 2019 to May 2021, prospective data acquisition was performed on 30 patients seen at the Department of Plastic, Hand, and Reconstructive Surgery at the University Hospital Regensburg, Germany (IRB reference number: 20-2081-101). In addition, comparative data were gathered from 10 healthy patients as the control group. The training set comprised 826 images, while the validation and testing sets consisted of 91 patient images each. Validation accuracy was 97.8% over the span of 64 epochs. The model was trained for 17.3 min. For training and validation, an average loss of 0.304 and 0.358 and a final loss of 0.276 and 0.157 were noted. The testing accuracy was observed to be 93.41% with a loss of 0.221. This study proposes a novel application for rapid and reliable lagophthalmos diagnosis. Our CNN-based approach combines effective anti-overfitting strategies, short training times, and high accuracy levels. Ultimately, this tool carries high translational potential to facilitate the physician's workflow and improve overall lagophthalmos patient care.

Application possibilities of artificial intelligence in facial vascularized composite allotransplantation-a narrative review

Facial vascularized composite allotransplantation (FVCA) is an emerging field of reconstructive surgery that represents a dogmatic shift in the surgical treatment of patients with severe facial disfigurements. While conventional reconstructive strategies were previously considered the goldstandard for patients with devastating facial trauma, FVCA has demonstrated promising short- and long-term outcomes. Yet, there remain several obstacles that complicate the integration of FVCA procedures into the standard workflow for facial trauma patients. Artificial intelligence (AI) has been shown to provide targeted and resource-effective solutions for persisting clinical challenges in various specialties. However, there is a paucity of studies elucidating the combination of FVCA and AI to overcome such hurdles. Here, we delineate the application possibilities of AI in the field of FVCA and discuss the use of AI technology for FVCA outcome simulation, diagnosis and prediction of rejection episodes, and malignancy screening. This line of research may serve as a fundament for future studies linking these two revolutionary biotechnologies.

ChatGPT Conquers the Saudi Medical Licensing Exam: Exploring the Accuracy of Artificial Intelligence in Medical Knowledge Assessment and Implications for Modern Medical Education

Background The application of artificial intelligence (AI) in education is undergoing rapid advancements, with models such as ChatGPT-4 showing potential in medical education. This study aims to evaluate the proficiency of ChatGPT-4 in answering Saudi Medical Licensing Exam (SMLE) questions. Methodology A dataset of 220 questions across four medical disciplines was used. The model was trained using a specific code to answer the questions accurately, and its performance was assessed using key performance indicators, difficulty level, and exam sections. Results ChatGPT-4 demonstrated an overall accuracy of 88.6%. It showed high proficiency with Easy and Average questions, but accuracy decreased for Hard questions. Performance was consistent across all disciplines, indicating a broad knowledge base. However, an error analysis revealed areas for further refinement, particularly with category (Option) A questions across all sections. Conclusions This study underscores the potential of ChatGPT-4 as an AI-assisted tool in medical education, demonstrating high proficiency in answering SMLE questions. Future research is recommended to expand the scope of training and evaluation as well as to enhance the model's performance on complex clinical questions.