Skip to main content
SMFM 2026 Pregnancy Meeting Main banner
Icon Legend
This session is not in your schedule.
This session is in your schedule. Click again to remove it.
Presentation Icons
Additional registration fee required
Additional registration fee required
Faculty have requested this content not be shared outside of the session
Faculty have requested this content not be shared outside of the session
CME Credit Offered
CME Credit Offered
Abstract Award
Abstract Award
Recording available 2/16-5/2
Recording available 2/16-5/2
AIUM Credit
AIUM Credit
Foundation Awardee
Foundation Awardee
Poster Icons
Abstract Award
Abstract Award
Foundation Awardee
Foundation Awardee

Poster Session 3

Category: Digital Health Technologies (DHT)

Poster Session 3

(741) Proactive AI Check-ins Rapidly Re-engage Patients with Gestational Diabetes: A Pilot Study

Thursday, February 12, 2026
10:30 AM - 12:00 PM  

    Submitting Author and Presenting Author(s)

  • Avish Arora, MD, PhD

    Fellow
    Montefiore/Albert Einstein College of Med.
    New York, New York, United States

    • Coauthor(s)

  • Pe'er Dar, MD

    Professor and Director, Division of Fetal Medicine
    Montefiore Medical Center
    Bronx, New York, United States

  • GD

    Georgios Doulaveris, MD

    Maternal Fetal Medicine Attending
    Montefiore Medical Center/Albert Einstein College of Medicine
    Montefiore Medical Center/Albert Einstein College of Medicine, New York, United States

Objective:

To evaluate the effectiveness of automated assistant-initiated check-ins in eliciting timely patient responses and promoting active self-management among newly diagnosed GDM patients.

Study Design:
In this prospective pilot study conducted from June 1–July 30, 2025, we enrolled ten pregnant individuals recently diagnosed with diet-controlled GDM. We developed a patient-facing, agentic AI tool for GDM that received FDA approval as an investigational device to support self-management. The WhatsApp-based assistant logged patient-reported glucose values, interpreted trends, offered tailored nutritional guidance, encouraged physical activity, and escalated concerning symptoms or readings. To enhance engagement, the assistant proactively delivered two types of automated check-ins: daily morning summaries (sent at 09:00 am, summarizing the previous three days and requesting fasting glucose and breakfast details) and inactivity prompts (triggered after 22 hours of no interaction, excluding quiet hours). Primary outcomes were the proportion of check-ins that received any patient response and those answered within 60 minutes.

Results:
During the study, the virtual assistant issued 498 automated check-ins, comprising 350 inactivity prompts (70%) and 148 morning summaries (30%). Patients replied to 318 (63.9%) of these automated messages. A total of 206 replies (39.7%) occurred within 60 minutes, with a median response time of 6.8 minutes (IQR 2.7–18.5). Five out of ten actively participating patients responded to over 90% of automated check-ins. Two symptom-related patient messages (one reporting dizziness, another nausea) were immediately escalated to clinicians within 15 minutes. No glucose-related safety alerts were missed.

Conclusion:
Automated conversational check-ins from an AI-powered GDM assistant effectively and rapidly re-engage patients without added clinician burden. A randomized controlled trial comparing traditional nutritional counseling with agentic AI–based diabetes management is underway.