Differentiating ChatGPT-Generated and Human-Written Medical Texts: Quantitative Study.

Wenxiong Liao Zhengliang Liu Haixing Dai Shaochen Xu Zihao Wu Yiyang Zhang Xiaoke Huang Dajiang Zhu Hong-Min Cai Quanzheng Li Tianming Liu Xiang Li

Published 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.

Keyphrases

machine learning
endothelial cells
healthcare
induced pluripotent stem cells
deep learning
high resolution
artificial intelligence