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.

Adverse vascular event management following hyaluronic acid-based aesthetic injections relies on the administration of hyaluronidase which is capable to enzymatically degrade the injected product and to improve clinical symptoms. Two protocols are currently available to manage such complications: “ultrasound guided targeted” and “flooding”. To compare the 2 protocols by means of amount of hyaluronidase volume utilized, and onset and degree of clinical improvement. A comparative case series of 39 patients was retrospectively evaluated which were initially treated with the “flooding” protocol and then treated with the “ultrasound guided targeted” due to no or little improvement. The “ultrasound-guided targeted” protocol utilized a total of 122.5 iu (34) whereas the “flooding” protocol utilized 1519.4 iu (1137) which represents a statistically significant reduced amount of injected hyaluronidase with p = 0.028. There was no clinical improvement in 92.3% and only little improvement in 7.7% of the treated patients following the first applied “flooding” protocol but there was a 100% immediate improvement when treated with the “ultrasound-guided targeted” protocol. Ultrasound imaging revealed that the application of hyaluronidase normal blood flow was restored both in the perivascular space and in the superficially located subdermal soft tissues. Despite its limitations in study design, this retrospectively evaluated case series revealed that the ultrasound guided targeted protocol utilized less hyaluronidase material and restored faster clinically visible symptoms. The effect of this protocol is best explained by the perforasome concept which will need to be investigated further in future studies.