RAPID: Collaborative Research: Mitigation and Suppression of Coronavirus Pandemic with Data-driven RAPID Decisions Using COVID-19 Simulator

2019冠状病毒病（COVID-19）是一场全球性大流行，已影响到人类生活的方方面面。虽然我们对COVID-19传播的理解仍在不断发展，但政策制定者需要在这种不确定性中做出战略决策，以缓解大流行。适当的政策决定可以降低发病率、死亡率和对医疗保健系统的损害。本研究将估算县一级COVID-19的潜在患病率，并预测在各种非药物和药物干预措施序列下COVID-19的未来发展轨迹。此外，这些新的估计和预测将纳入我们现有的在线COVID-19模拟器（www.covid19sim.org），为县级决策提供信息。此外，COVID-19模拟器将发现社区级COVID-19疫情的早期迹象，并预测不同司法管辖区的热点。从社会角度来看，这项研究将提高我们对COVID-19传播的认识，并为减轻病毒传播的政策提供信息，最终减少COVID-19疾病负担。本研究将采用流行病学和运筹学建模方法，模拟COVID-19在县域的传播，以及不同干预措施对缓解COVID-19的影响。此外，将使用因果决策树和基于混合整数规划的机器学习算法来识别县级传播热点。拟议的研究不仅将为具有重要公共卫生意义的关键决策提供信息，而且还将贡献智力优势，包括1)近乎实时地链接和使用各种数据集，以提高我们对疾病流行病学的理解；2)估计COVID-19的潜在患病率并预测各种干预措施下的未来轨迹；3)开发实时参数估计、模型校准和预测的创新方法。(4)利用流行病学、统计学和基于机器学习的建模技术发现社区级COVID-19疫情的早期迹象。该奖项由环境生物学部的传染病生态和进化项目利用冠状病毒援助、救济和经济安全（CARES）法案的资金设立。该奖项反映了美国国家科学基金会的法定使命，并通过基金会的智力价值和更广泛的影响审查标准进行评估，被认为值得支持。

Coronavirus disease 2019 (COVID-19), a global pandemic, has affected every sector of human life. While our understanding of the spread of COVID-19 is still evolving, policymakers need to make strategic decisions amidst this uncertainty to mitigate the pandemic. Appropriate policy decisions can reduce morbidity, mortality, and damage to the healthcare system. This study will estimate the underlying prevalence of COVID-19 at the county level and project future trajectories of COVID-19 under various sequences of non-pharmaceutical and pharmaceutical interventions. In addition, these new estimations and projections will be incorporated into our existing online COVID-19 Simulator (www.covid19sim.org) to inform county-level decisions. In addition, the COVID-19 Simulator will detect early signs of community-level COVID-19 outbreaks and predict hotspots in different jurisdictions. From a societal perspective, this research will improve our understanding of COVID-19 transmission and inform policies to mitigate the spread of the virus, ultimately leading to a reduction in COVID-19 disease burden.This research will use epidemiological and operations research modeling approaches to simulate the spread of COVID-19 at the county level and the effects of different interventions on mitigation of COVID-19. In addition, causal decision tree and mixed-integer programing-based machine learning algorithms will be used to identify county level hotspots of transmission. The proposed research will not only inform key decisions with important public health implications, but also contribute to intellectual merits, including 1) linking and using various datasets in near real-time to improve our understanding of disease epidemiology, 2) estimating the underlying prevalence of COVID-19 and projecting future trajectories under various interventions, 3) developing innovative approaches for real time parameter estimations, model calibrations, and projections, and (4) detecting early signs of community-level COVID-19 outbreaks using epidemiological, statistical and machine learning based modeling techniques.This RAPID award is made by the Ecology and Evolution of Infectious Diseases Program in the Division of Environmental Biology, using funds from the Coronavirus Aid, Relief, and Economic Security (CARES) ActThis 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.