Predict, Prevent, Protect: AI in High-Risk Pregnancies

Department

Department of Population Health Management and Policy, Hairston College of Health and Human Sciences, North Carolina Agricultural & Technical State University

Document Type

Poster

Publication Date

4-17-2026

Abstract

Background: Artificial intelligence (AI) is increasingly integrated into healthcare to improve access, efficiency, and clinical decision-making. However, its application for high-risk pregnancies remains limited. Given the intensive monitoring needs of Medicaid beneficiaries, understanding how AI has been used in high-risk obstetric care is critical for informing equitable access. Methods: A scoping review of the literature was conducted using databases such as PubMed and Web of Science, along with targeted journal searches. We also included grey literature from agencies such as CDC and AHRQ. We conducted a title-abstract screening of 285 articles and selected 50 for full-text review. We identified 20 articles that met the criteria. Results: The preliminary results highlight emerging but limited evidence supporting the use of AI-enabled tools for high-risk pregnancies, particularly for monitoring, patient education, and early detection of conditions such as hypertensive disorders. Existing applications, such as Pregbot and Malama, demonstrated potential to enhance communication and self monitoring; however, studies also highlighted persistent limitations related to usability, readability, and the timeliness of clinical information. Notably, only a few tools were designed with Medicaid beneficiaries in mind. Based on these findings, we are developing a concept for an AI-based application tailored to the needs of Medicaid beneficiaries in North Carolina. Conclusion: Current evidence suggests that AI-enabled tools have the potential to support early identification, monitoring, and patient engagement in high-risk pregnancies, but existing applications are limited in their equity-focused design. Future research will use community-based participatory research to refine and validate an AI-based application with Medicaid beneficiaries and healthcare experts in North Carolina.

This document is currently not available here.

Share

COinS