ChatGPT가 한국 신경과 의사들에게 실제 임상에서 유용할까?

초록

Background: Since the emergence of artificial intelligence (AI), such as ChatGPT, there has been extensive research on its utility in the medical field. This study evaluates the potential of utilizing the ChatGPT AI platform to provide specialized advice to Korean neurologists. Methods: Through a multifaceted approach, it assesses both the knowledge and practical clinical utility using neurology training evaluation questions and clinical case reports. Results: The accuracy of ChatGPT in answering medical exam questions (45.1%) is comparable to or slightly lower than previous studies. The study also examines performance of ChatGPT in providing advice based on clinical case reports, finding that while it can offer suitable diagnostic suggestions and propose relevant tests in some cases (8/12), its overall diagnostic accuracy is limited (2/12). Limitations include the platform’s text-based nature, which hinders the interpretation of image-based questions, and the uneven distribution of case reports across subfields. Conclusions: Despite these limitations, ongoing advancements in AI technology offer prospects for improved performance and expanded applications in the medical field, warranting continued research and monitoring of AI’s role in medicine.

키워드