AI in obstetrics: Evaluating residents’ capabilities and interaction strategies with ChatGPT

In line with the digital transformation trend in medical training, students may resort to artificial intelligence (AI) for learning. This study assessed the interaction between obstetrics residents and ChatGPT during clinically oriented summative evaluations related to acute hepatic steatosis of pregnancy, and their self-reported competencies in information technology (IT) and AI. The participants in this semi-qualitative observational study were 14 obstetrics residents from two university hospitals. Students' queries were categorized into three distinct types: third-party enquiries; search-engine-style queries; and GPT-centric prompts. Responses were compared against a standardized answer produced by ChatGPT with a Delphi-developed expert prompt. Data analysis employed descriptive statistics and correlation analysis to explore the relationship between AI/IT skills and response accuracy. The study participants showed moderate IT proficiency but low AI proficiency. Interaction with ChatGPT regarding clinical signs of acute hepatic steatosis gravidarum revealed a preference for third-party questioning, resulting in only 21% accurate responses due to misinterpretation of medical acronyms. No correlation was found between AI response accuracy and the residents' self-assessed IT or AI skills, with most expressing dissatisfaction with their AI training. This study underlines the discrepancy between perceived and actual AI proficiency, highlighted by clinically inaccurate yet plausible AI responses - a manifestation of the 'stochastic parrot' phenomenon. These findings advocate for the inclusion of structured AI literacy programmes in medical education, focusing on prompt engineering. These academic skills are essential to exploit AI's potential in obstetrics and gynaecology. The ultimate aim is to optimize patient care in AI-augmented health care, and prevent misleading and unsafe knowledge acquisition.