Evaluating the Efficacy of GPT-based Nutrition and Diabetic Counseling in Gestational Diabetes Management: A Randomized Controlled Trial (AIM-GDM)

Gestational diabetes mellitus (GDM) affects approximately 6-9% of pregnancies globally, posing significant risks to both maternal and neonatal health. Standard management includes dietary counseling, glucose monitoring, and insulin therapy when necessary. However, the rising prevalence of GDM and limited healthcare resources necessitate innovative solutions to supplement traditional care. Generative Pre-trained Transformers (GPTs), a type of large language model (LLM), offer personalized, real-time counseling and support. Recent advancements in AI have shown promise in various healthcare applications, but the efficacy of GPT-based counseling in GDM management remains underexplored. This study builds on preliminary evidence suggesting that AI can enhance patient engagement and outcomes, aiming to validate these findings in a controlled trial.

The integration of AI, specifically GPTs, into healthcare can revolutionize patient management by providing continuous, tailored support. This study aims to evaluate whether GPT-based counseling can improve glycemic control and patient satisfaction in GDM management, compared to traditional counseling alone. By placing AI within the context of prenatal care, this research seeks to address gaps in current GDM management practices and offer scalable, personalized solutions.