A critical perspective on large language model to obtain clinical information about fertility research

I read a recent article by Chervenak et al. ( 1 Chervenak J. Lieman H. Blanco-Breindel M. Jindal S. The promise and peril of using a large language model to obtain clinical information: ChatGPT performs strongly as a fertility counseling tool with limitations. Fertil Steril. 2023; 120: 575-583 Abstract Full Text Full Text PDF PubMed Scopus (11) Google Scholar ), “The promise and peril of using a large language model to obtain clinical information: ChatGPT performs strongly as a fertility counseling tool with limitations,” with great interest. The exploration of artificial intelligence (AI) applications in the domain of reproductive medicine is indeed a crucial field of study. The investigators deserve commendation for their pioneering work, although I would like to highlight some critical considerations about the approach and conclusions. The promise and peril of using a large language model to obtain clinical information: ChatGPT performs strongly as a fertility counseling tool with limitationsFertility and SterilityVol. 120Issue 3PreviewTo compare the responses of the large language model-based “ChatGPT” to reputable sources when given fertility-related clinical prompts. Full-Text PDF Open AccessReply of the authors: looking beyond “promise and peril”Fertility and SterilityVol. 120Issue 5PreviewStanding on the banks of the Rubicon in Italy—a line which represents a point of no return—Julius Caesar is famously thought to have said, “alea iacta est” (the die is cast). We believe the same could be said regarding artificial intelligence (AI) in health care. Full-Text PDF