The George Washington University (GW) School of Medicine and Health Sciences (SMHS) is pioneering a significant advancement in healthcare through a new partnership with the University of Maryland Eastern Shore (UMES). Fueled by an $839,000 grant, this collaboration aims to develop cutting-edge Artificial Intelligence (AI) tools, metaphorically representing medical care tools silhouette, designed to empower frontline health workers serving communities with limited resources.
This innovative project, aptly named “Trustworthy AI to Address Health Disparities in Under-resourced Communities,” or AI-FOR-U, is embedded within the larger Artificial Intelligence/Machine Learning Consortium to Advance Health Equity and Researcher Diversity (AIM-AHEAD) initiative, supported by a $1.9 million grant from the National Institutes of Health (NIH). AI-FOR-U is dedicated to establishing a theory-driven, participatory framework for the creation of dependable AI instruments for health disparities research.
Spearheading this crucial endeavor at GW SMHS is Dr. Qing Zeng, a distinguished 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. Working in tandem with Dr. T. Sean Vasaitis, dean and professor at the UMES School of Pharmacy and Health Professions, the research team will focus on constructing and implementing AI/machine learning algorithms that enhance fairness and improve the interpretability of risk-prediction models – essentially refining the “medical care tools silhouette” to be more transparent and equitable. These refined AI tools will undergo rigorous evaluation through three practical clinical scenarios focusing on cardiometabolic disease, oncology, and behavioral health, areas identified as high priority by community partners and stakeholders. A key aspect of the evaluation will be to measure the degree of trust that frontline healthcare providers place in these AI-driven tools.
Dr. Zeng highlights that this project is a direct response to the biomedical research community’s growing need for trustworthy AI in healthcare, particularly in addressing the complex challenges of diversity and health equity. This concern resonates deeply within both expert and community stakeholder groups.
“Our approach is unique in that we are intentionally integrating theory-driven community engagement with the practical application and rigorous testing of trust-enhancing algorithms throughout the tool development process,” Dr. Zeng explained. “The selection and direction of the clinical use cases are community-led, driven by the priorities identified by our partners and stakeholders. Even in the project’s initial planning stages, several risk prediction models have already emerged as critical areas of focus for our community partners.”
This partnership strategically combines UMES’s recognized expertise in health disparities with GW’s established leadership in AI development. The overarching goal is to enhance healthcare decision-making processes while simultaneously fostering opportunities for advancing AI education at both institutions. In addition to Dr. Zeng, the GW project team includes prominent figures such as Dr. LaQuandra Nesbitt, senior associate dean for population health sciences and health equity, 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; Dr. Yijun Shao, associate director of data science of BIC; Linda Zanin, EdD, director of strategic partnerships at SMHS; and Dr. Senait Tekle, post-doctoral research fellow.
UMES is equally well-represented, with a team of five faculty members collaborating with Dr. Vasaitis. This team includes Dr. Timothy Gladwell, associate dean for academic affairs and assessment; Dr. Miriam Purnell, chair and professor in the Department of Pharmacy Practice and Administration; Dr. Yen Dang, professor and director of Global Health; Dr. Omar Attarabeen, associate professor; and Dr. Jocelyn Reader, assistant professor.
The AI-FOR-U project is deeply rooted in community needs, collaborating with seven community partners that serve diverse populations across Washington, D.C., Maryland, and Virginia. These populations include Black, Latino, and LGBTQ+ minorities, as well as individuals with lower socioeconomic status and new immigrants in the region. Participating organizations span healthcare, education, and community sectors, and 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. These community partners will be actively involved through focus groups, interviews, and community surveys, providing invaluable input and feedback on the AI tools and their effectiveness in addressing health disparities from the perspectives of patients, providers, and administrators.
Dr. Vasaitis emphasizes the transformative potential of AI in healthcare but also underscores the critical need for responsible development and implementation. “The increasing integration of artificial intelligence in healthcare holds immense promise for revolutionizing patient treatment and developing solutions for pressing health challenges,” Dr. Vasaitis stated. “While we recognize the significant benefits of these technologies, we are acutely aware of our responsibility to ensure that AI deployment does not exacerbate existing health inequities or compromise patient care through reliance on biased datasets. Furthermore, enhancing user understanding of AI’s decision-making processes is paramount. Trust in AI-driven insights and the ability to assess their accuracy are essential. The AI-FOR-U project is specifically designed to address these crucial concerns by creating trustworthy AI applications that genuinely meet the needs of healthcare professionals serving underserved and underrepresented populations, refining the ‘medical care tools silhouette’ to be both powerful and equitable.”
The AIM-AHEAD coordinating center receives support from NIH under OT2OD032581 to the University of North Texas Health Care Center.
[Insert image of medical tools in silhouette here, e.g., a stethoscope, syringe, and pills, fading into an AI brain or network silhouette in the background to represent AI in medicine. If no suitable image is found, omit this section.]
Alt text for the image (if included): Silhouette of medical tools merging into an AI network, symbolizing trustworthy medical care tools silhouette development for equitable healthcare access.
