RAPID: Combining Big Data in Transportation with Hospital Health Data to Build Realistic "Flattening the Curves" Models during the COVID-19 Outbreak

COVID-19在美国的爆发为研究人员提供了一个重要的机会，可以改进平坦化曲线模型，这些模型可用于评估甚至在空间上优化快速扩大的大流行期间的医疗保健。这个快速响应研究（Rapid）项目将利用大规模可用的位置传感设备和应用程序，这些设备和应用程序产生关于移动模式的大数据，可用于更好地优化医疗设施的使用。这项研究将快速展开的健康数据与流动性的实时数据结合在一起。我们将研究如何将这两种关键数据资源联系起来，以便在大流行期间更好地为政策提供信息，确定新出现的热点，并确定关键行动的目标。这项研究将有助于政府官员更好地了解和适应突发卫生事件发生和扩大时不断变化的情况。“扁平化曲线”图表的传播对于促进公众了解社交距离的重要性具有重要意义。然而，这些曲线是基于模拟数据。这项研究将收集和检查流动性数据和公共卫生数据，利用真实数据建立平坦化曲线模型。我们将来自基于位置的应用程序和手机的大数据与UMMS医院的电子医疗记录相结合，包括COVID-19测试数据、患者人口统计数据和预后。定量衡量集体运动行为变化以应对快速发展的COVID-19疫情的新建模方法将与医院的使用和容量联系起来。这项研究的方法将扩展我们对交通和卫生等高度综合系统的认识，并使公众更好地为未来的灾难做好准备。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

The outbreak of COVID-19 in the U.S. provides an important opportunity for researchers to improve flattening curve models which can be used to assess and even spatially optimize health care during a rapidly expanding pandemic. This Rapid Response Research (RAPID) project will take advantage of the large-scale availability of location-sensing devices and apps that produce big data on mobility patterns that can be used to better optimize the use of healthcare facilities. This research brings together rapidly unfolding health data with real-time data on mobility. We will examine how these two critical data resources can be linked to better inform policy, identify emerging hotspots, and target critical actions during a pandemic. This research will help public officials to better understand and adapt to changing conditions as a health emergency arises and expands.The spread of the “flattening curves” graphic was significant in promoting public understanding of the criticality of social distancing. These curves, however, were based on simulated data. This research will collect and examine mobility data and public health data to model flattening curves using real data. We combine big data from location-based apps and cellphones with Electronic Medical records from UMMS hospitals, including data on COVID-19 tests, and patient demographics and prognostics. New modeling approaches that quantitatively measure change in collective movement behaviors in response to the fast-evolving COVID-19 outbreak will be linked to hospital usage and capacity. The methods of this research will extend our knowledge of highly integrated systems, like transportation and health, and better prepare the public for future disasters.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.