How can we create ����������������community food security���������������? This project aims to develop a community-based socially intelligent nonprofit food rescue and distribution infrastructure to fairly serve vulnerable communities experiencing food insecurity. This infrastructure will have a loop mechanism that continuously learns consumer preferences and provides feedback to upstream stages of the supply chain and also learns about the food availability at the local food sources and feeds that information to the downstream stages. The main objective of this research is to minimize food waste along different stages of the supply chain while maximizing equitable access to safe food given consumer preferences. Food banks are nonprofit organizations that provide a framework for the non-profit food supply chain by collecting donations from multiple sources such as local grocers, growers, and the community (e.g., food drives) and distributing the donations to food-insecure households through a network of community-based partner agencies (e.g., food pantries, homeless shelters, schools). The COVID-19 pandemic has significantly strained this network as demand has surged, the volunteer-based workforce has waned, and supply uncertainty has increased highlighting both the network������������������s strengths and limitations and the need to strengthen the community-based infrastructure and create solutions that are self-reliant and robust for communities that are affected by such events.

Diabetic retinopathy (DR) is expected to affect over 11 million people in the US by 2030 and is the leading cause of blindness in working age Americans, despite being almost entirely preventable with timely detection, treatment, and adherence to follow-up care. To reach the over 30 million adults living with diabetes in the US, the Retinal Care-DR program is designed to eliminate the deficiencies of the current care delivery model by implementing a first-of-its-kind, end-to-end solution for DR care and blindness prevention. This will be accomplished through the application of machine learning to prioritize patients for care coordination by DR risk, development of patient-specific engagement strategies to identify and modify adherence behaviors, implementation of agent-based simulation to maximize patient health outcomes while minimizing the cost of care coordination, and the identification of care coordination strategies that result in higher rates of screening using a user-centered design process.

The COVID-19 Simulation Integrated Modeling (COVSIM)CovSim2 team brings deep experience in infectious disease modeling and engagement with public health agencies, including work on COVID-19 (as part of first year of funding from CDC and CSTE 2020-2021) and on influenza pandemic (2007 to 2018). Across the team, there is also previous experience in modeling and decision-making for cholera, malaria, HIV, Hepatitis C, guinea worm disease, obesity, diabetes, sepsis, and more. We pair our deep computational experience with domain expertise in public health, communication, and visualization to elicit feedback and disseminate results. Our team has extensive experience building complex models in a variety of clinical and policy settings and using them to inform decision making.

Matriculation and Well-Being Under Emergent Events (MWEE), will harness data from four campuses, engage communities and encourage the development of processes and actions to address this global challenge and answer questions such as: Can we measure and assess our ability to create virtual community through synchronous and asynchronous learning? Can we use data to inform real time risk stratification within campus community? Can we evaluate the effect of social distancing policies enacted on campuses? In doing so, we expect universities to be able to layer the results with data from their campuses to predict retention and graduation rates given emergent events including COVID-19.

The COVID-19 pandemic has intensified interest in health systems������������������ ability to prepare for, and cope with, surges (sudden large-scale escalations) in the treatment needs of critically ill patients. Several studies in the literature and the US Department of Health and Human Services provide recommendations and standard operating procedures for intensive care unit (ICU) and hospital preparations for a mass disaster or pandemic. However, due to the rarity of the events and the lack of a mechanism to gather data in real-time, the implementation of these recommendations in a healthcare organization usually depends on the experience of hospital emergency managers rather than evidence-based approaches. Furthermore, the scale, velocity, and global impact of the COVID-19 pandemic is beyond what any plans had anticipated. In this proposal, we aim to document medical surge capacity preparations and real-time adjustments for the COVID-19 pandemic in two major hospital systems: (1) Prisma Health, the largest not-for-profit health organization in South Carolina, serving more than 1.2 million patients annually; and (2) MedStar, a not-for-profit healthcare organization operating more than 120 entities, including ten hospitals in the Baltimore������������������Washington, DC area.

While current models of the COVID-19 pandemic have been helpful for initial national and state-level planning, the ability of local government, public health, and health care system leaders to utilize these simpler models to evaluate specific containment, mitigation, and operational strategies is limited. Next-level decision support models need to be representative of the local population and environment, and include interactions between people, resources, and policies. Our multidisciplinary team proposes to develop an integrated simulation model that captures both COVID-19 progression within an individual, within census tracts, and aggregated to counties and the state level. Key elements include socio-demographics such as age, gender, race, and geographic information that locates individuals within households, workplaces, and schools. Example performance measures of the robabilistic forecasts include cases, hospitalizations, deaths over time and by location. Interventions will be incorporated such as school closures, distancing, face coverings, therapeutics, and vaccinations, to result in averted cases, hospitalizations, and deaths. Our proposal builds on established work in influenza and COVID-19, developing and communicating forecasts to key decision makers. The team will conduct interviews with stakeholders to ensure relevance of policies and results. The focus is on rapid development and innovation with communication across multiple platforms.

Nonprofit hunger relief organizations operate in a complex environment consisting of a large and diverse donor base and a dynamic distribution network. These organizations generate a large amount of unstructured and complex data on food collection, inventory management, and distribution activities. However, existing information systems lack the infrastructure to interpret this large-scale data to provide real-time policy recommendations and support operational and strategic decision-making. The proposed smart service system will synthesize data from disparate sources to create a real-time perspective of the environment and learn from the actions of the decision maker. Specifically, this system will automatically predict, visualize, and recommend decisions that will advance operational effectiveness of food collection, distribution, and resource management in a way that is efficient and equitable and will identify opportunities to improve a food bank������������������s capability to satisfy hunger need.

Following the landfall of hurricane Florence, thousands of families including children and seniors are out of power, food and water. Food Bank of Central and Eastern North Carolina (FBCENC), as one of the food banks serving in this area, is now operating at extended capacity to recover from the storm. FBCENC is facing an unique situation as 22 counties of their service territory fall within the affected area including two of their branch locations. Many of their partner agencies are still out of operation and it took about two weeks after the storm to bring the affected FBCENC branches back in operation. The purpose of this RAPID NSF project is to document the challenges encountered by FBCENC after Hurricane Florence. Specifically, we intend to collect data to quantify the extent of this disruptive event in order to provide insight on how nonprofit food distribution organizations can prepare, respond, and recover from disruptions to their network. Food Bank networks are unique in that normal operations involve responding to another type of disaster (hunger need) which is considered slow onset. However, given a sudden onset disaster, they simultaneously meet the existing hunger need within their service area while responding to the needs of the population in the affected area. This is particularly complicated if the affected area lies within their service area, which can bring increased demand given transportation network and capacity uncertainty.

The goal of the EMPOWER Center is to address disparities at the intersection of health, wealth, and education by developing methods for harnessing, securing, synthesizing and learning from structured and unstructured data from multiple traditionally unconnected sources to inform and empower communities. We propose to develop a learning data-enabled intelligent community wellness monitoring system using gaming and virtual reality (i.e., an advanced smart simcity which are digital twins of real communities) to enable policy makers, community leaders and individuals to easily visualize trade-offs, measure/assess consequences of policies and choices, and optimize to improve decision making.

A critical period for the retention of highly skilled women in STEM (Science, Technology, Engineering, and Mathematics) is the postdoctoral and early career tenure-track faculty stage. These women have advanced technical training, are poised to train the next generation of scientists and engineers, and are on the cusp of productive, innovative careers. STEM cannot afford to lose this talent. To address this critical issue, we intend to submit a PLAN-D proposal to adapt, study, and share a successful multi-day symposium for advancing early career women in STEM.