SCC-IRG Track 2: SCHOLAR: Smart, Connected, and Healthy Outcomes from Leveraging Assets and Research

An effective method for improving health outcomes for high-risk patients in under-resourced communities is the implementation of a Community Health Worker (CHW) program. There is an urgent need to integrate emerging technologies into these programs to help CHWs better link patients with health and social service providers in the community, and better support health systems to address the social determinants of health.

SCHOLAR (Smart, Connected, and Healthy Outcomes from Leveraging Assets and Research) will leverage the voices of CHWs to build the health system’s ability to use data to predict patient needs and provide better care. This approach uses data to build an information pipeline between community members and the health systems that serve them, strengthening the smart connection between them.

As a result of this work, hospitals will be equipped with the right data to assign their time, talent, and resources to improve health outcomes. In the long run, this innovative sociotechnical approach will lead to more sustainable health systems in under resourced communities by reducing Emergency Department (ED) readmission rates, which are a key metric for federal funding programs.

The SCHOLAR project will design, develop, and evaluate an analytics dashboard that will empower CHWs to interact with and interpret data and lead to: 1) improved computational prediction modeling for Emergency Department readmission rates; 2) improved health system risk stratification and resource allocation; and, 3) strengthening of the smart connection between the health system and the communities it serves. The project will be deployed in overburdened and under-resourced South and Southwest Side Chicago communities served by Sinai Chicago, Illinois' largest private safety net hospital system.

This integrative research spans social science and technology domains. The project team includes researchers from DePaul University and Sinai Urban Health Institute (the community-engaged research arm of Sinai Chicago), with expertise in data science and machine learning, human computer interaction, epidemiology, and community based public health. Grounded in our previous work, we will investigate: 1) data linkage across healthcare and community settings including Electronic Medical Record and social determinants of health data integration; 2) high-risk stratification prediction models that take into account diverse patient groups; 3) human-computer interaction approaches that aim to iteratively incorporate CHW feedback into design, development, and implementation of prediction models; and 4) prototypes of training, networks, and participatory structures to systemize an integrative SCHOLAR CHW program that leverages the advantages of data-informed decisions and the efficiency of computational tools.

This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.