The grant abstract summary information shown below was originally provided by the applicant. However, HRSA has edited it to remove any phone numbers and email addresses that were included. The summary you see is from the most recent submission.
Project Name: Maternal Health Research Network (MH-RN) for MSIs--Research Awards (UR6)
Applicant Title: MEHARRY MEDICAL COLLEGE
Abstract Text: Project Title: Developing a Comprehensive Data Analytics Infrastructure Model to Support Maternal Healthcare for Underserved Women with Substance Use Disorders Applicant Organization Name: Meharry Medical College Address: 1005 Dr. D.B. Todd Jr. Blvd, Nashville, Tennessee, 37208 Project Principal Investigator: Aize Cao, PhD, Phone: xxx-xxx-xxxx, xxxx@xxx.xxx; Lloyda B. Williamson, MD, Project Co-Principal Investigator, Phone: xxx-xxx-xxxx, Fax: xxx-xxx-xxxx, xxxxxxxxxxx@xxx.xxx Website Address: http://www.mmc.edu/ Problem: The increased risk of pregnancy-related complications associated with substance use affects African American and the underserved communities disproportionately. Pregnant and postpartum women struggling with substance use face significant challenges that imped their well-being and adversely affect the healthy development of their children. The problem is understanding the barriers of this health disparities in order to help address this crisis. Priorities and Goals: Our primary focus is to develop a comprehensive patient centered data analytics infrastructure model that prioritizes the needs of African American pregnant and postpartum women struggling with substance use in Nashville, TN at a Historically Black Academic Medical Center, with an ultimate goal to positively impact the well-being of pregnant and postpartum women nationwide. We will focus on three key priorities to achieve this goal in the next five years: 1) support substance abuse residential treatment and recovery program for pregnant and postpartum women within the Elam Mental Health Center (EMHC), the behavioral health service arm of the Department of Psychiatry and Behavioral Health at Meharry Medical College (Meharry), one of the historically black medical colleges (HBCU) in the United States. 2) address health disparities and investigate the social determinant of health (SDoH) and other risk factors that contribute to the high risk pregnant-related complications associated with substance use disorders (SUD) and mental health; 3) advance maternal health studies within the biomedical data science program of Meharry’s School of Applied Computational Sciences. Methodology: We will accomplish the goals through a comprehensive data analytics infrastructure model leveraging data science techniques and patient care model. We will 1) establish a multi-modality data infrastructure, which will involve clinical chart review, collecting and integrating patient survey and brain imaging data. 2) identify SDoH information from patient survey and electronic health records (EHR), explore factors that advance or impede the substance use treatment and recovery; 3) explore the relationship of brain functional connectivity and maternal substance use and relapse; 4) build predictive models using EHR from Meharry, the Tennessee State Department of Health, and NIH All of Us program. Students will participate, scientific report will be presented for education and increased awareness of maternal healthcare. Product: Successfully completion of the proposed studies will lead to: an enhanced data infrastructure, an SDoH identification approach, an established neuroimaging analysis pipeline, predictive models, scientific publications, and evidence being gained to support the residential treatment programs at EMHC for underserved pregnant and postpartum women with SUD. Evaluation: This project will use an external evaluator to conduct a formative, outcome-based program evaluation that will demonstrate success in achieving stated objectives for maternal health outcomes improvement. Key Terms: Maternal health, Rainbow program, substance use, mental health, data infrastructure, SDoH, EHR, neuroimaging, natural language processing, machine learning, predictive modeling