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

Montefiore Medicine Academic Health System

Status: Enrolling

Conditions: Gestational Diabetes

Treatments: Other: Nutritional Counseling; Device: GPT-based counseling

Study type: Interventional

Funder types: Other

Identifiers

NCT06582719

2024-16035

Details and patient eligibility

About

The purpose of this study is to assess whether an AI based counseling service can be beneficial for patients to assist in management of gestational diabetes.

Full description

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.

Enrollment: 80 estimated patients

Sex: Female

Ages: 18 to 45 years old

Volunteers: Accepts Healthy Volunteers

Inclusion criteria

• Women aged 18-45
• Diagnosed with GDM in pregnancy
• Able to use a smartphone
• Fluent in English or Spanish

Exclusion criteria

• Pre-existing diabetes
• High-risk pregnancies due to other medical conditions
• Inability to consent
• Non-English and/or Non-Spanish speakers
• No smartphone access

Trial design

Primary purpose: Treatment

Allocation: Randomized

Interventional model: Parallel Assignment

Masking: Single Blind

---

80 participants in 2 patient groups

Nutritional Counseling plus AI Intervention

Experimental group

Treatment:

Device: GPT-based counseling

Other: Nutritional Counseling

Nutritional Counseling

Active Comparator group

Treatment:

Other: Nutritional Counseling