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

Faculty have requested this content not be shared outside of the session

CME Credit Offered

Abstract Award

Recording available 2/16-5/2

AIUM Credit

Foundation Awardee

Poster Icons

Abstract Award

Foundation Awardee

Poster Session 3

Category: Digital Health Technologies (DHT)

Poster Session 3

(908) Artificial Intelligence as a Prenatal Support Tool: How Does AI Compare to Standard Clinical Guidance?

Thursday, February 12, 2026

10:30 AM - 12:00 PM

Submitting Author and Presenting Author(s)

Olivet Martinez, MD (she/her/hers)

Baylor Scott & White All Saints Medical Center
Fort Worth, Texas, United States

Coauthor(s)

TM

T Morgan Moody, DO

Baylor Scott & White All Saints Medical Center
Fort Worth, Texas, United States
AB

April Bleich, MD

Baylor Scott & White All Saints Medical Center
Baylor Scott & White All Saints Medical Center, Texas, United States
KH

Kollier Hinkle, MD

Baylor Scott & White All Saints Medical Center
Fort Worth, Texas, United States

Objective:
Artificial intelligence (AI) has gained popularity in healthcare and conversational AI chatbots have become widely accessible in recent years. Pregnant individuals often seek health information online and this trend is especially prevalent in patients with difficulty accessing health care services. The purpose of this study was to assess the accuracy, readability, and empathy of AI-generated responses to common pregnancy questions.

Study Design:
This cross-sectional study analyzed AI chatbot responses to 10 pregnancy-related questions. Questions were input into four AI chatbots: ChatGPT, Meta AI, Google Gemini, and Grok. Each response was evaluated across three metrics: accuracy, determined by comparing responses to guidelines from the American College of Obstetricians and Gynecologists; readability, assessed using the Flesch Reading Ease Score; and empathy, measured using a scale adapted from the Empathetic Communication Coding System.

Results:
Accuracy of chatbot responses was high with all responses assessed as completely accurate (40% of responses) or partially accurate (60% of responses). Accuracy did not differ significantly across chatbots (p = 0.337). However, statistically significant differences were observed in readability (p = 0.0099) and empathy (p = 0.035). ChatGPT had significantly higher readability scores than Meta AI (p = 0.028) and Grok (p = .008). ChatGPT also demonstrated significantly higher empathy scores than Google Gemini (p = 0.019).

Conclusion:
Although all chatbots provided similarly accurate information, ChatGPT ranked highest in delivering responses that were more readable and emotionally supportive compared to Google Gemini, Meta AI, and Grok. This highlights the potential of AI to serve as a prenatal support tool, delivering accurate and accessible information to meet the informational and emotional needs of expectant patients during pregnancy.