Creating SDoH-informed Chicagoland Data Repositories

The institute will provide an umbrella to connect the cutting-edge research in data science that is currently happening separately all across the UIC ecosystem in its 16 colleges and UI Hospital system. This connecting structure will nurture collaboration and networking, maintain a comprehensive repository of resources and activities, and, most importantly, present a single, streamlined entity for funding agencies. This trust is synergetic with the other two thrusts.

We will establish and advance an SDoH-informed data repository that can be accessed and utilized by investigators across the UIC system. We seek to improve data access and monitoring across the UIC campus and beyond; and leverage data warehouses. The data repository will partner with existing structures and frameworks rather than duplicating efforts. Existing efforts include:

 

  • The UIC Center for Clinical and Translational Sciences (CCTS) and its Biomedical Informatics Core manages UIC’s Clinical Research Data Warehouse (CRDW), a research data repository that provides a secure, managed release point for human subjects’ data for use in research. Dr. Pasupathy, one of the Data Science Institute investigators, is the co-Director of the CCTS Biomedical Informatics core. The UIC CRDW contains curated data from diverse sources, including the Electronic Health Records (EHR), Genetics and other OMICs, Imaging data, Vital records, Death records, Medical billing and Legacy systems, and others. The “address AI” tool being developed by the CTTS biomedical informatics core is designed to provide for user-friendly data query to investigators.
  • The Population Health Analytics Metrics and Evaluation (PHAME) Center at the UIC School of Public Health provides an extensive data repository for hyperlocal data on SDOH, neighborhood and community factors and diverse set of health indicators in the City of Chicago and the Suburban Cook County. Dr. Basu, a Data Science Institute investigator, is the PI of the PHAME Center whose mission is to democratize data for public health. Besides extensive data on health, SDoH and neighborhood, the PHAME Center additionally provides data on Chicago Environmental Justice Index, Unmet Mental Health Needs, and links with the City of Chicago’s New Arrivals Situational Awareness Dashboard on new arrivals from the southern border that the City of Chicago has welcomed.
  • The Chicago Health Atlas  provides all the outcomes that the Chicago Department of Public Health collects. The Cook County Health Atlas provides all the health outcomes that the Cook County Department of Public Health collects. Other external datasets include COSMOS, which comprises de-identified electronic health records for ~226 million patient cases and 9.8 billion patient encounters that are nationally-representative for age, race, ethnicity, and coverage in the U.S. UIC is an early adopter of this new dataset, leading the nation.
  • The proposed UIC P20 Center for Climate Change and Health Equity will develop an integrated database for climate-related environmental and social exposures and health disparities.

These rich resources of multimodal data will provide extensive opportunities for data science innovations and funding opportunities. The heterogeneous data resolutions (individual vs. hyperlocal), as well as data ownership and privacy concerns, for example, will also provide intriguing research questions in concepts, theory and advancing data science methodologies.