Our laboratory specializes in the integration and analysis of complex, multilevel data resources in order to study how the neighborhood, or environment where a person lives, together with a person’s behavior and biology, can impact cancer risk and cancer health disparities.  Specifically, our laboratory develops machine learning and geospatial methods to discover patterns in complex, multilevel risk factor data that can be used to improve clinical risk prediction models for patients and to ensure targeted cancer prevention efforts are deployed to communities disproportionately impacted by poor cancer outcomes.  In line with Precision Public Health, our emphasis is not only on identifying patients or communities with higher than expected rates of cancer or identifying multilevel risk factors (e.g. genetic, biologic, behavioral, and neighborhood or environmental factors) from existing disease surveillance resources, but translating this information into action through cancer interventions.  Our work is currently supported by funding from the Department of Defense, the American Cancer Society, and the Pennsylvania Department of Health.

Research Interests