Recent research explores how Large Language Models can automate medical history-taking in obstetrics and gynecology, potentially transforming clinical workflows.

• Evaluates LLMs' ability to conduct sensitive medical conversations, particularly for infertility cases
• Assesses both conversational quality and diagnostic accuracy metrics
• Addresses potential for reducing physician time burden while maintaining quality care
• Examines the feasibility of AI assistance in complex, sensitive medical domains

This research matters because it demonstrates practical applications of AI to address healthcare efficiency challenges in specialized fields, potentially reducing wait times and improving access to care while maintaining quality standards.

Evaluating the Feasibility and Accuracy of Large Language Models for Medical History-Taking in Obstetrics and Gynecology