1. Evaluating artificial intelligence responses to respiratory medicine questions.
- Author
-
Luo, Hong, Yan, Jisong, and Zhou, Xia
- Subjects
- *
ARTIFICIAL intelligence , *ACINETOBACTER infections , *CHATGPT , *NATURAL language processing , *MEDICAL terminology - Abstract
This article evaluates the use of an artificial intelligence tool called ChatGPT in the field of respiratory medicine. ChatGPT is designed to provide human-like responses to a wide range of topics, including medical inquiries. However, there are concerns about its accuracy and reliability in the medical sector, as it has not been extensively trained with biomedical datasets or vetted by medical professionals. The study found that ChatGPT provided correct answers for 63.5% of respiratory medicine questions, with higher accuracy in basic medical knowledge and lower accuracy in treatment and management. It is important to note that ChatGPT should not replace professional medical advice and should be used with caution. The article highlights the limitations of ChatGPT and suggests that it can be used as a supplementary educational tool under expert guidance. Future research should focus on improving the model's accuracy and reliability in specialized domains like respiratory medicine. [Extracted from the article]
- Published
- 2024
- Full Text
- View/download PDF