SUNY ESF
Center for Environmental Medicine and Informatics

With a significant portion of human disease influenced by environmental exposures, an improved understanding of these links along with rapid translation of such findings into public health policy and clinical practice is critical. Experts at ESF, SUNY Upstate Medical University, and Syracuse University will work together to fill this gap by creating a formal structure for collaboration centered on the application of big data, artificial intelligence, scientific computing, and informatics to pressing environmental health problems.

It is now widely recognized that a significant portion of human disease is influenced by environmental exposures. An improved understanding of these links along with rapid translation of such findings into public health policy and clinical practice is critical if we are to reduce the burden of environmentally induced disease. On a national level, leadership is needed in the area of translational research as applied to environmental medicine and experts at SUNY ESF, SUNY Upstate Medical University, and Syracuse University are interested in and well-positioned to begin filling this gap. It is crucial to create a formal structure for collaboration centered on the application of big data, artificial intelligence, scientific computing, and informatics to pressing environmental health problems.

With support from the Discovery Challenge, we will create essential infrastructure for a self- sustaining Center for Environmental Medicine and Informatics (CEMI). Such a partnership builds directly on the recent Empire Innovation Program (EIP)-supported faculty lines in the field of Environmental Health, and we will seek an additional EIP hire with relevant expertise early in the seed period. Based on the current work and research interests of collaborators on this proposal, an initial CEMI research portfolio will include (but not be limited to): environmental links to cancer and Parkinson's disease; health disparities in morbidity and mortality and small area variations in environmental quality; as well as the relationships between environmental stressors (e.g., toxicants, discrimination) and cardiovascular disease risk. These conditions frequently involve multiple exposures (the "exposome") with multiple potential mediators (e.g., genomic and other "–omic" profiles) affecting multiple interrelated outcomes. Therefore, strong capabilities in big data analytics, machine learning, and bioinformatics are necessary because of the range, complexity, and fragmentation of the data that must be aggregated and analyzed in support of the research agenda.