SCH: Synergizing Topological Deep Learning and Spatio-Temporal Causal Inference to Unpack Health

PROJECT SUMMARY (See instructions): This research aims to provide novel statistical and deep learning (DL) tools to address open methodological challenges in understanding and mitigating health disparities in the United States in the context of the climate crisis. It focuses especially on the health effects of extreme heat and air pollution.

Marginalized populations often bear the brunt of climate threats. It is thus vital to identify the communities and individuals that are most vulnerable. To enable such analysis, this multi-disciplinary research brings together computer scientists and biostatisticians to promote principled and synergistic advancements in

Topological Deep Learning (TDL) and spatial Causal Inference (Cl) to address open technical challenges in the fields of TDL, Cl, and Spatial Statistics. The project is centered around three thrusts. Thrust 1: Develop new TDL methods to process multi-resolution irregular areal data; Thrust 2: Leverage TDL in

spatiotemporal causal inference; Thrust 3: Establish a methodological framework to jointly leverage TDL-based spatial and individual-level representations. Innovations include new TDL methods to address key gaps in DL for areal spatial data, the first theoretically grounded framework leveraging TDL for

learning from aggregated outcomes under spatial heterogeneity in areal data, and new TDL methods for causal inference using spatiotemporal data. This project will result in the first multi-modal scalable framework for learning joint representations of geospatial data and individual-level health records.

Large-scale case studies utilizing Medicare data from 2000 to 2020 and a vast amount of spatial and longitudinal data will allow the translation of research results into actionable information to inform policies and interventions to reduce health disparities. The successful completion of this research will address

scientific policy-relevant questions such as: Which social and structural determinants of health lead to higher vulnerability to hospitalization and death caused by extreme heat, and, therefore, more urgently need mitigation policies to ensure climate justice? How does exposure to air pollution exacerbate

geographic health disparities due to exposure to heat over the short- and long-term? Does individual-level medical history contribute to recurrent hospitalizations among individuals of low socioeconomic status?