NSF RAPID: Modeling Corona Spread Using Big Data Analytics

新型冠状病毒新冠肺炎是一种临床表现严重的病毒，包括死亡。尽管新冠肺炎的最终走向和影响尚不确定，但公共卫生努力在很大程度上取决于准确预测新冠肺炎如何在全球传播。在新的疫情爆发期间，当可靠的数据仍然稀缺时，研究人员会求助于数学模型，这些模型可以预测可能被感染的人会去哪里，以及他们带来疾病的可能性有多大。这个过程有时涉及到对未知因素的假设，比如旅行模式。然而，通过插入每种输入的不同可能版本，研究人员可以在新信息可用时更新模型，并将他们的结果与观察到的疾病模式进行比较。在这个项目中，我们建议使用创新的大数据分析技术和工具来开发一个新冠肺炎传播模型。我们将利用埃博拉传播模型研究的经验，成功地模拟冠状病毒传播。我们希望获得新的结果，这将有助于减少感染甲型病毒的患者数量和相关死亡人数。由于我们的合作伙伴拥有庞大的数据库(通过我们与LexisNexis的合作)，我们建议采用“自动”流程，这样我们就可以快速识别病毒在社区中的运行轨迹，从而显著降低感染率和死亡人数。拟议的研究活动具有极大的潜力，可以促进大数据分析领域以及医疗、医疗保健和公共应用等不同领域的知识进步。我们建议通过使用创新的大数据分析技术和工具来开发一个COVID传播模型，以了解冠状病毒传播模式将被输入公共卫生系统的决策支持系统(DSS)。根据传播模式，DSS将计算社会团体或地区感染冠状病毒的概率。这些数据将以报告的形式提交给负责的州和政府机构，这些机构随后将立即采取行动检测和遏制病毒热点。我们将与LexisNexis Corporation密切合作，LexisNexis Corporation是美国领先的数据分析公司，也是我们的NSF I/UCRC for Advanced Knowledge Enablement的成员。LexisNexis致力于为我们的计算模型研究提供大量数据，以预测这种疾病的传播，利用前向模拟和向后模拟，跟踪一些已验证的感染。在许多研究中，数学分区模型已被成功地应用于预测疾病暴发的行为。这些模型旨在了解疾病传播过程的动态，并专注于将人口划分为几种健康状态。常见的假设可以包括：个体数量、感染概率、潜伏期、感染恢复时间等。这些现象学假设限制了模型的范围，同时保留了模型最现实的方面，但一些模型维度假设是必要的，因为实际数据不存在。因此，在我们的研究中，我们计划使用拟议的新兴技术来加速美国疾病传播方面的知识积累。在我们的研究中，我们计划计算与日冕扩散相关的各种得分，包括：人口密度等级、家庭死亡率风险、街道水平死亡率风险和县死亡率风险。该项目将帮助佛罗里达大西洋大学和LexisNexis建立联盟，利用计算机科学、大数据分析、数据可视化技术和决策支持系统的最新技术，共同解决具有国家和全球意义的公共卫生问题。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

The novel coronavirus COVID-19 is a virus with serious clinical manifestations, including death. Although the ultimate course and impact of COVID-19 are uncertain, public health efforts depend heavily on accurately predicting how COVID-19 spreads across the globe. During new outbreaks, when reliable data are still scarce, researchers turn to mathematical models that can predict where people who could be infected are going and how likely they are to bring the disease with them. This process sometimes involves making assumptions about unknown factors, such as travel patterns. By plugging in different possible versions of each input, however, researchers can update the models as new information becomes available and compare their results to observed patterns for the illness. In this project we propose developing of a model of COVID-19 spread by using innovative big data analytics techniques and tools. We will leverage experience from research in modeling Ebola spread to successfully model Corona spread. We expect to obtain new results, which will help in reducing the number of infected a patients and related deaths. Because of our partner's large database (through our collaboration with LexisNexis), we are proposing "automatic" process, so we can quickly identify the virus' trajectory in a community to significantly reduce the infection rate and the number of deaths. The proposed research activities have a great potential to advance knowledge within the field of big data analytics as well as across different fields including medical, healthcare, and public applications. We propose to develop a model of COVID spread by using innovative big data analytics techniques and tools to understand Corona spread patterns will be fed into a Decision Support System (DSS) for public health systems. Based on spread patterns, the DSS will then calculate probabilities for a social group or area will get infected with Corona. The data will be presented in the form of reports to responsible state and government agencies, who will then immediately take action of testing and containing virus hotspots. We will closely collaborate with LexisNexis Corporation, which is a leading US data analytics company and a member of our NSF I/UCRC for Advanced Knowledge Enablement. LexisNexis is committed to provide a large amount of data for our study of computational models to predict the spread of this disease utilizing both, forward simulation and the propagation of the infection into the community and backward simulation, tracing a number of verified infections. Mathematical compartmental models have been successfully applied to predict the behavior of disease outbreaks in many studies. These models aim to understand the dynamics of a disease propagation process and focus on partitioning the population into several health states. Common assumptions can include: number of individuals, infection probability, incubation period, infected recovery time, etc. These phenomenological assumptions limit the scope of the model while preserving the most realistic aspects of it, but some model dimension assumptions are necessary because actual data does not exist. Therefore, in our research we plan to use of the proposed emerging technologies could accelerate the accumulation of knowledge around disease propagation in the United States. In our research we plan to calculate various scores related to Corona spread including: Population density rank, Household mortality risk, Street level mortality risk, and County mortality risk. The project will help build a coalition between Florida Atlantic University and LexisNexis to jointly address public health problems of national and global significance using the state of the art in computer science, big data analytics, data visualization techniques, and decision support systems.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.