Artificial Intelligence in Medical Writing: Addressing Untouched Threats

Abstract

The advantages and disadvantages of the use of generative artificial intelligence, such as ChatGPT, in medical writing have been widely discussed; however, two concerns remain largely unexplored. The first involves "human touch," such as personal anecdotes and experiences. This touch often distinguishes human-written papers from those generated by ChatGPT as ChatGPT cannot independently access personal experiences. Although ChatGPT may mimic humanlike behavior, including the incorporation of a human touch, it lacks genuine emotions. With the lack of established guidelines on the acceptable levels of ChatGPT use and imperfect detection tools, many authors fear that their work could be perceived as overly reliant on ChatGPT. I worry that writers may artificially insert forced personal touches simply to assert their own writing. The second concern is the authors' worry and doubt about whether to use ChatGPT and, if so, to what extent, which may disrupt their reflective and quiet writing process. While I acknowledge the lack of empirical data, I offer practical suggestions to balance the benefits of ChatGPT assistance and the preservation of the integrity of human writing in medical publications.

Ähnliche Arbeiten