RAPID: COVID-19 Coronavirus Testbed and Knowledge Base Construction and Personalized Risk Evaluation

点击翻译按钮获取中文摘要

The 2019 novel coronavirus disease (COVID-19) is an evolving epidemic. There is little knowledge about COVID-19’s outbreak and spread patterns, and the impact of viral evolution, demography, social behavior, cultural differences, and quarantine policies on the outbreaks. As the battle against COVID-19 continues, a deluge of information is being produced. Academia, news agencies, and governments continuously publish advances in the understanding of the virus clinical pathologies, its genome sequences, and relevant administrative policies and actions taken. Nevertheless, the dramatic outbreak differences with respect to diverse geographies, regional policies, and cultural groups also raise confusion, contradictions, and inconsistencies in disease outbreak modeling. It is therefore crucial to build a knowledge base of COVID-19 to understand the correlations and roles that different factors play in predicting the spread of the virus, thus enabling both individuals and health care officials to implement appropriate policies to mitigate the effects of the epidemic on public health and society at large. This project will create a COVID-19 coronavirus testbed and knowledge base, as well as a personalized risk evaluation tool for individuals to assess their infection risk in a dynamic environment. The technical aims of the project include two thrusts. The first creates a testbed and knowledgebase that includes information for modeling outbreak and mutation of COVID-19. This testbed will serve as a benchmark for the public to model and understand the spread of COVID-19, and eventually mitigate the negative effects of COVID-19 on public health, society, and the economy. The second thrust develops a multi-source deep neural network-based predictive tool to combine demographics, policies, regional infections, and individual information for personalized risk evaluation. As a result, the public can employ personalized information to estimate their infection risk level, using social and behavioral information (e.g., family size, shopping patterns, and dining patterns), local authority policies (e.g., school, restaurant, and movie theater closures as well as night time curfew), demographics (e.g., population age, density, and income), health condition (e.g., heart disease incidence, cancer prevalence, and substance abuse), and regional virus condition (e.g., number of infection cases in the region studied and infection rate).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.