Project Summary/Abstract Structural racism, defined as the ways in which societies foster discrimination through mutually reinforcing inequitable systems, has emerged as an important social risk factor and contributor to poor health outcomes for racial/ethnic minorities (Egede 2020, Bailey 2017). Structural racism captures upstream historic racist events (such as slavery, black code laws, Jim Crow laws, and school segregation) and more recent state sanctioned racist laws in the form of redlining. Redlining refers to the practice of systematically denying various services to residents of specific neighborhoods/communities, often based on race/ethnicity (Bailey 2020). A first important link between historic redlining and health outcomes is likely related to health care access in the form of accessible hospital and neighborhood clinics, as well as the quality of these facilities. A second important linkage between historic redlining and health outcomes is likely associated with the way in which structural racism (in the form of redlining) has systematically deprived neighborhoods of economic opportunities, and as such, of the ability to build individual and community assets in the form of housing value, employment, and educational opportunities for its residents. These linkages between structural racism, access, community assets, and health disparities, are furthermore of significant current policy relevance as recent trends indicate a growing number of hospital and clinic closures due to the COVID-19 pandemic (Ellison 2021). However, the link between historic redlining and urban hospital and clinic closures as well as community assets and community health outcomes are poorly understood. The goal of this project is to inform our understanding of the pathways between structural racism (defined as historic redlining), urban hospital and clinic closures, community assets, and health outcomes; and to further inform policies that can help reduce the impact of structural racism on health disparities caused by hospital and clinic closures. The present study seeks to accomplish this objective by using recently developed causal and interpretable machine learning methods, along with econometric counterfactual analysis, to address the following aims: 1) Examine the relationship between regional exposure to structural racism and the propensity of hospital and clinic closures. 2) Examine the relationship between hospital and clinic closures and community employment, income, and education, as well as community health outcomes. 3) Predict risk of closure among urban hospitals and clinics that are disproportionately serving racial/ethnic minorities from neighborhoods with exposure to structural racism. 4) Undertake stakeholder engagement to address prevention of future closures and/or examine ways to decrease the potential adverse community impact of hospital and clinic closures. The study is innovative in its examination of the linkages between structural racis...