Conventional environmental health studies have primarily focused on limited environmental stressors at the population level, which lacks the power to dissect the complexity and heterogeneity of individualized environmental exposures. There are countless physical, social, psychological, and built environmental exposures people experience in their daily lives which are known to impact their health and shape gene expression through epigenetic mechanisms. As our understanding of health and disease continues to progress, it becomes increasingly important for scholars across the natural, social, and health sciences to work together to ensure that health risks present in the built and social environment be identified and attributed for.
Newer data driven approaches including machine learning and Artificial Intelligence allow unprecedented opportunities to integrate multiple data streams and unravel the complexities of complex cardiometabolic diseases. Our laboratory uses a variety of approaches including personal biometric and health data, imaging based precision radiomic measures, together with geo-spatial approaches and high-throughput sequencing, to understand the impact of aggregate exposures and internal multi-omics to systematically investigate how the exposome shapes a single individual’s phenome.
Overall, this data-driven approach shows the potential dynamic interactions between the personal exposome and multi-omics, as well as the impact of the exposome on precision health by producing abundant testable hypotheses. Case Health Innovation Programs comprise of 2 Laboratories. The first is a geo-spatial unit to allow integration of place based social and environmental big data features with health measures and other environmental exposures at the population level. This is the Specialized Program in Integrated Fine Scale Cartographic-Enabled Socio-Environmental Risk (SPICES). The second, Cardiovascular Health and Artificial Intelligence (CHAI), is a cardiovascular phenomics laboratory with an emphasis on harnessing machine learning and Artificial Intelligence approaches. The laboratory uses Precision Imaging Measures such as CT, MRI and Optical Coherence Tomography images and radiomic analysis of features tounderstand personalized predictors of disease. Additionally, CHAI Personal Monitoring Technologies couples these information streams with other environmental and place based determinants from SPICES to develop next generation precision exposomic measures that can provide inputs for a digital health trajectory.