Differentiating ChatGPT-Generated and Human-Written Medical Texts: Quantitative Study.
Wenxiong LiaoZhengliang LiuHaixing DaiShaochen XuZihao WuYiyang ZhangXiaoke HuangDajiang ZhuHong-Min CaiQuanzheng LiTianming LiuXiang LiPublished in: JMIR medical education (2023)
Although text generated by ChatGPT is grammatically perfect and human-like, the linguistic characteristics of generated medical texts were different from those written by human experts. Medical text generated by ChatGPT could be effectively detected by the proposed machine learning algorithms. This study provides a pathway toward trustworthy and accountable use of large language models in medicine.