The George Washington University (GW) School of Medicine and Health Sciences (SMHS) received a two-year, $839,000 grant to partner with the University of Maryland Eastern Shore (UMES) on the development of Artificial Intelligence (AI) tools to help frontline health care workers serving under-resourced populations.
The project, “Trustworthy AI to Address Health Disparities in Under-resourced Communities,” or AI-FOR-U, is part of a larger $1,9 million grant Artificial Intelligence/Machine Learning Consortium to Advance Health Equity and Researcher Diversity (AIM-AHEAD) and the National Institutes of Health (NIH) to design a theory-based, participatory development approach for creating trustworthy AI tools for health disparities research.
Leading the effort at GW SMHS is Qing Zeng, PhD, professor of clinical research and leadership, director of GW’s Biomedical Informatics Center (BIC), and co-director of Data Science Outcomes Research at the Washington DC Veterans Affairs Medical Center. Along with T. Sean Vasaitis, PhD, dean and professor in the UMES School of Pharmacy and Health Professions, researchers will develop and implement AI/machine learning algorithms to enhance the fairness and improve the ability to explain risk-prediction models. The resulting AI tools will then be evaluated through three clinical-use cases in the areas of cardiometabolic disease, oncology, and behavioral health as selected by community partners and their stakeholders. The team will measure the impact of the frontliners’ trust of the AI tools.
According to Zeng, the project will help address a concern in the biomedical research community about developing trustworthy AI tools to address diversity challenges in health care in both expert and stakeholders’ communities.
“We will combine theory-driven community engagement with the application and testing of trust-enhancing algorithms in the tool development,” she said. “The clinical use cases outcomes will be driven and selected by our partners and stakeholders. In the preparation of the project, a few risk prediction models, have emerged as shared high priorities for our partners.”
The partnership pairs UMES-expertise in health disparities with GW’s success in AI development to improve health care decision-making while building opportunities to advance AI education at both institutions. Besides Zeng, GW members of the project team include: LaQuandra Nesbitt, MD, MPH, senior associate dean for population health sciences and health equity, Bicentennial Endowed Professor of Medicine and Health Sciences, and executive director of the Center for Population Health Sciences and Health Equity at SMHS; Melissa Goldstein, JD, teaching associate professor at the Milken Institute School of Public Health at GW; Yijun Shao, PhD, associate director of data science of BIC and associate research professor; Linda Zanin, EdD, director of strategic partnerships at SMHS; and Senait Tekle, PhD, post-doctoral research fellow.
Five UMES faculty members are working on the project with Vasaitis include: Timothy Gladwell, PharmD, associate dean for academic affairs and assessment and associate professor; Miriam Purnell, PharmD, chair and professor, Department of Pharmacy Practice and Administration, and program director, PBC Rural Health Disparities and Social Inequities; Yen Dang, PharmD, professor and director of Global Health; Omar Attarabeen, PhD, associate professor; and Jocelyn Reader, PhD, assistant professor.
The project team will work with seven community partners serving diverse populations from Washington, D.C., Maryland, and Virginia, including Black, Latino, and LGBTQ+ minorities, as well as people with lower socioeconomic status, and/or new immigrants in the region. The health care, educational, and community organizations participating include: Alexandria City (Virginia) Public Schools, Apple Discount Drugs, the Organization of Chinese Americans-DC, Saint Elizabeths Hospital, Unity Healthcare, Virginia State University, and Whitman Walker Health. The community partners will participate in focus groups, interviews, and community surveys. The partners’ patients, providers and administrators will provide input and feedback on the AI tools and their success at addressing health disparities.
“The continuing implementation of artificial intelligence in health care will have profound effects on both our methods of treating patients and on the development of solutions for many of our pressing issues,” Vasaitis said. “While we recognize the potential for great benefit inherent in these technologies, we also understand our responsibility to ensure that the use of AI does not increase health care inequity or lead to improper patient care through reliance on unrepresentative datasets. Additionally, there is a need to improve the AI user's understanding of how and why AI generates a response. We need to be able to trust the answers, and we need a way to judge how accurate the answers are likely to be. The AI-FOR-U project is designed to address these concerns by creating trustworthy AI applications that meet the needs of health care workers in underserved and underrepresented populations.”
The AIM-AHEAD coordinating center is supported by NIH under OT2OD032581 to University of North Texas Health Care Center.
