RAPID: Collaborative Research: VAPOC: Visualization, Analysis and Prediction of COVID-19

点击翻译按钮获取中文摘要

Preliminary statistical analysis of COVID-19 data shows that African Americans are more affected by COVID-19 than other ethnic groups in the USA. Recent data from the Centers for Disease Control and Prevention (CDC) confirms that the black population accounted for 30% of cases of the virus in the United States, although it is only approximately 13% of the US population. In New York city, an epicenter of COVID-19, data also show that the black population represents 28% of deaths due to COVID-19. The goal of the VAPOC (Visualization, Analysis and Prediction of COVID-19) project is to find out reasons as to why the black community is disproportionately impacted during the coronavirus pandemic. It seems a combination of factors is responsible for African Americans’ susceptibility to COVID-19. This poses a pattern recognition as well as knowledge discovery problem. It is hypothesized that pre-existing conditions, type of employment, and access to healthcare among other factors have significant influences in the higher death rate of African Americans during the COVID-19 pandemic. The visualization, analysis, and prediction of COVID-19 in the African American community is necessary for: 1) the community to be well informed about measures to ameliorate the impact of coronavirus and to reduce its spread, and 2) a proper understanding of what factors medical professionals should prioritize when performing health assessments and diagnostic tests for COVID-19 patients. VAPOC will also help decision-makers to improve mitigation strategies. This project is a collaborative effort between the University of the District of Columbia and Bowie State University.To accomplish the research goal, the three research objectives of this project are: 1) to design, develop and evaluate a COVID-19 model to determine vulnerability to coronavirus; 2) to develop a visualization and interaction tool to analyze COVID-19 patients’ data in an immersive and non-immersive environment, and evaluate how graphical objects (such as data-shapes) developed in accordance with the user’s requirements can enhance situational awareness; and 3) to design, develop and evaluate a deep learning model to predict the extent of COVID-19 damage to discharged patients. VAPOC combines neural network predictions with human-centric situational awareness and data analytics to provide accurate, timely and scientifically-based strategy for combating and mitigating the spread of the novel coronavirus in the black community. Ultimately, understanding how COVID-19 affects the black community will also provide criteria for mitigating the spread of future outbreaks. Furthermore, the project will leverage research in deep learning, data analytics and data visualization to provide information that could be used to inform the allocation of resources and institutional policies to reduce the disparity of COVID-19 deaths in the African American community.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.