From Fragmented to Findable: Navigating the SDOH Data Landscape with Integrated Discovery Ecosystem
July 23, 2025 11:00 am (Central Time)
Abstract
Public health research increasingly depends on integrating diverse datasets related to the social determinants of health (SDOH), such as demographics, environmental conditions, economic indicators, and community resources. Yet researchers, especially those new to SDOH domains, often face challenges in discovering relevant data due to specialized terminology and fragmented distribution across multiple agencies. In this presentation, we will provide an overview of the SDOH & Place Data Discovery application, a project of the Healthy Regions & Policies Lab that combines a Flask-based metadata management system with a search and discovery web interface built through human-centered design. The platform provides standard facet-based search as well as an AI-powered conversational interface that leverages OpenAI’s API for natural language interpretation. The AI-powered search incorporates validation through a Solr-based metadata search engine, enabling researchers to explore the insights of geospatially relevant datasets, including social indexes, environmental monitoring data, transportation networks, and community resource inventories. By prioritizing metadata exploration over basic data storage, our system lowers the barrier to entry for SDOH research and empowers researchers to more easily identify, understand, and utilize place-based health determinants data critical for their analysis.
Speakers
Pengyin Shan
National Center for Supercomputing Applications, University of Illinois Urbana-Champaign
Pengyin Shan is a Senior Research Software Engineer at the National Center for Supercomputing Applications (NCSA). She has extensive full-stack development experience supporting academic institutions across the U.S. and Canada. Her work focuses on building accessible web applications that make use of complex datasets across domains such as smart geospatial systems, digital agriculture, and bioinformatics. She holds a B.S. in Computer Science Engineering from The Ohio State University and an M.B.A. from York University. She is also an active member of the U.S. Research Software Engineer Association and a certified CyberAmbassador facilitator, promoting communication and teamwork in scientific computing.
Shubham Kumar
University of Illinois Urbana-Champaign
Shubham is a Senior Product Designer at Healthy Regions & Policies Lab, with a passion for collaborating with diverse teams to achieve design goals. His work spans across the design spectrum, ranging from gathering requirements to creating high-fidelity designs for health equity projects at the lab. Prior to his current role, Shubham was improving accessibility in education with the Board of Trustees at the University of Illinois. He has a master’s degree in Information Management from the University of Illinois Urbana-Champaign and hails from Bangalore, the Silicon Valley of India.
Adam Cox
University of Illinois Urbana-Champaign
Adam is a senior research software engineer at Healthy Regions & Policies Lab, with a background in geospatial programming and GIS. He leads engineering and infrastructure development in the lab, primarily focusing on the SDOH & Place Project but also supporting projects like the US Covid Atlas, Chicago Environment Explorer and the Opioid Environment Policy Scan data ecosystem. He holds an MS in Geography and MLIS from Louisiana State University. Originally from Wisconsin, he lives in New Orleans, Louisiana with his wife and small cat.