According to the Centers for Disease Control and Prevention, more than 40% of adults with depression are obese and adults with depression are more likely to be obese than adults without depression. Combined together, depression and obesity are two of the most common public health problems in the United States. Yet, effective exercise programs that help people to lose weight and cope with depression symptoms do not always reach communities with the greatest need. Mining data through electronic health records (EHR) and digital health technology can help to improve the reach by identifying communities most affected by obesity and depression. Once identified, engaging those communities is critical to informing locally-tailored interventions that will be adopted. The purpose of this project is to build capacity for combining health data analytics with community engagement efforts to identify, and design better interventions for, communities facing obesity and depression.

This project (1) integrates heterogeneous data sources, machine learning, and geospatial analysis to identify geographical areas with high levels of depression and obesity called community hotspots, and (2) engages community members from hotspots to co-design desired physical activity interventions. Project findings will advance the field by yielding new ways for hotspot detection based on diverse real-world data and community-level intervention design while laying the technical and collaborative foundations necessary for future success. Technical contributions include novel data analytic methods, data sources, and metrics for hot-spotting using regional EHR data. Collaborative partnerships developed through this project will guide future extension of engagement to a broader number of community hotspots. More broadly, this work will benefit society through a data-driven, community-partnered approach that improves the health and wellbeing of citizens by addressing two of the most significant US health problems: depression and obesity.