Surgeon or Bot? The Risks of Using Artificial Intelligence in Surgical Journal Publications

Artificial Intelligence: A Help or Hindrance to Scientific Writing?

We have assessed the chatbot Generative Pretrained Transformer, a type of artificial intelligence software designed to simulate conversations with human users, in an experiment designed to test its relevance to scientific writing. chatbot Generative Pretrained Transformer could become a promising and powerful tool for tasks such as automated draft generation, which may be useful in academic activities to make writing work faster and easier. However, the use of this tool in scientific writing raises some ethical concerns and therefore there have been calls for it to be regulated. It may be difficult to recognize whether an abstract or paper is written by a chatbot or a human being because chatbots use advanced techniques, such as natural language processing and machine learning, to generate text that is similar to human writing. To detect the author is a complex task and requires thorough critical reading to reach a conclusion. The aim of this paper is, therefore, to explore the pros and cons of the use of chatbots in scientific writing.

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.