Diagnostic and Management Performance of ChatGPT in Obstetrics and Gynecology

Abstract

Objectives: The use of artificial intelligence (AI) in clinical patient management and medical education has been advancing over time. ChatGPT was developed and trained recently, using a large quantity of textual data from the internet. Medical science is expected to be transformed by its use. The present study was conducted to evaluate the diagnostic and management performance of the ChatGPT AI model in obstetrics and gynecology. Design: A cross-sectional study was conducted. Participants/Materials, Setting, Methods: This study was conducted in Iran in March 2023. Medical histories and examination results of 30 cases were determined in six areas of obstetrics and gynecology. The cases were presented to a gynecologist and ChatGPT for diagnosis and management. Answers from the gynecologist and ChatGPT were compared, and the diagnostic and management performance of ChatGPT were determined. Results: Ninety percent (27 of 30) of the cases in obstetrics and gynecology were correctly handled by ChatGPT. Its responses were eloquent, informed, and free of a significant number of errors or misinformation. Even when the answers provided by ChatGPT were incorrect, the responses contained a logical explanation about the case as well as information provided in the question stem. Limitations: The data used in this study were taken from the electronic book and may reflect bias in the diagnosis of ChatGPT. Conclusions: This is the first evaluation of ChatGPT’s performance in diagnosis and management in the field of obstetrics and gynecology. It appears that ChatGPT has potential applications in the practice of medicine and is (currently) free and simple to use. However, several ethical considerations and limitations such as bias, validity, copyright infringement, and plagiarism need to be addressed in future studies.