The elevated risk of pregnancy-related complications alongside substance use during pregnancy is a critical public health crisis that impacts both the mother and their developing children. Pregnant and postpartum women affected by substance use experience complex and intersecting challenges, including co-occurring physical and mental health conditions and persistent barriers to high-quality care. These challenges disproportionately burden underserved and low-income populations. This project seeks to address these disparities by leveraging artificial intelligence (AI) and machine learning (ML) to advance maternal health research, identify key risk factors, and inform data-driven interventions that promote health and recovery for vulnerable women.

We are committed to improving maternal health outcomes through the power of data science, population health informatics, and artificial intelligence. Our work focuses on uncovering hidden patterns in maternal health disparities, developing early detection and risk prediction models, and addressing the urgent need to reduce preventable maternal morbidity and mortality, particularly among low-income women who are disproportionately affected by these challenges.

A core initiative of our project is the development of a comprehensive, patient-centered data analytics infrastructure to support pregnant and postpartum women experiencing substance use and mental health conditions, with a particular focus on those receiving care at Meharry’s Lloyd C. Elam Mental Health Center. In parallel, we examine diverse populations across multiple data sources, ranging from local clinical records to national databases such as the NIH All of Us Research Program. By leveraging AI/ML methods, we aim to generate actionable insights that advance maternal health research and inform data-driven care.

Equally important, we prioritize training a diverse next-generation workforce in maternal health informatics, equipping future leaders with the skills and commitment needed to translate data into evidence-based solutions that improve maternal health outcomes