Large language models (LLMs) in radiology exams for medical students: Performance and consequences

Purpose The evolving field of medical education is being shaped by technological advancements, including the integration of Large Language Models (LLMs) like ChatGPT. These models could be invaluable resources for medical students, by simplifying complex concepts and enhancing interactive learning by providing personalized support. LLMs have shown impressive performance in professional examinations, even without specific domain training, making them particularly relevant in the medical field. This study aims to assess the performance of LLMs in radiology examinations for medical students, thereby shedding light on their current capabilities and implications. Materials and Methods This study was conducted using 151 multiple-choice questions, which were used for radiology exams for medical students. The questions were categorized by type and topic and were then processed using OpenAI's GPT-3.5 and GPT- 4 via their API, or manually put into Perplexity AI with GPT-3.5 and Bing. LLM performance was evaluated overall, by question type and by topic. Results GPT-3.5 achieved a 67.6% overall accuracy on all 151 questions, while GPT-4 outperformed it significantly with an 88.1% overall accuracy (p<0.001). GPT-4 demonstrated superior performance in both lower-order and higher-order questions compared to GPT-3.5, Perplexity AI, and medical students, with GPT-4 particularly excelling in higher-order questions. All GPT models would have successfully passed the radiology exam for medical students at our university. Conclusion In conclusion, our study highlights the potential of LLMs as accessible knowledge resources for medical students. GPT-4 performed well on lower-order as well as higher-order questions, making ChatGPT-4 a potentially very useful tool for reviewing radiology exam questions. Radiologists should be aware of ChatGPT's limitations, including its tendency to confidently provide incorrect responses.