A significant hurdle in the development of methodologies and advancement of theory regarding data types used for answering question about energy and spatial context is turning large data sets collected from sensors into usable values for epidemiologic statistical models, dealing with data error and missingness, as well as integrating diverse types of sensor data and environmental exposures. 

Machine learning methods are increasingly permeating various scientific disciplines as well as popular science. However, there are significant hurdles to applying these methods into public health and behavioral health ranging from interpretation of outputs to explaining how the methods produce results.

​​These papers focus on recent research on cancer-related health disparities, with a specific focus on data integration of large geospatial datasets with a range of omics and clinical outcomes.

Development and adaptation of web applications for the City of Hope catchment area to aid Community Outreach and Engagement efforts.