在防控新型冠状病毒感染的肺炎疫情斗争中，政府、医疗机构、科研部门、科技企业和非政府组织迅速行动，把大数据、人工智能等技术应用到疫情监测分析、人员管控、医疗救治、复工复产等各个方面，发挥了作用，为疫情防控工作提供了支撑。
本课题将研究新冠疫情背景下大数据对卫生政策实施产生的影响。传染病动力学模型（SEIR模型）一直被广泛运用于SARS、COVID-19等传染性疾病的建模和流行趋势的预测。前期我们使用SEIR模型开展了预测武汉市、湖北省和中国湖北省以外地区COVID-19流行趋势的研究，其预测趋势与实际数据拟合度较好，为这次的研究打下了理论基础。SEIR模型有三个重要变量，分别是基本再生数（R0）、有效再生数（Re）和随时间变化的有效再生数（Rt）。R0在预测传染病的流行中起着至关重要的作用，它代表了由原发感染者产生继发病例的平均数量 。Rt代表原发病例在时间t内可能产生的平均继发病例数 。由于世界各地防控策略的制定和防控措施的实施不尽相同，因此各地的流行趋势也存在显著差异。依据不同国家和地区的背景来估计R0和Rt的值有助于更好地预测全球流行趋势。
In the prevention and control will be coronavirus pneumonia outbreak in the struggle, the government and medical institutions, scientific research department, technology companies and ngos to act quickly, the large data, such as artificial intelligence technology is applied to the epidemic monitoring and analysis, personnel control, medical treatment, from various aspects, such as return to work and production has played a role, provides support for epidemic prevention and control work.
This project will study the impact of big data on health policy implementation in the context of COVID-19. Infectious disease dynamics model (SEIR model) has been widely used to model and predict the epidemic trend of infectious diseases such as SARS and COVID-19. In the previous stage, we used the SEIR model to predict the epidemic trend of COVID-19 in Wuhan, Hubei Province and regions outside Hubei Province of China. The predicted trend had a good fit with the actual data, which laid a theoretical foundation for this study. SEIR model has three important variables, which are basic regeneration number (R0), effective regeneration number (Re) and effective regeneration number with time (Rt). R0 plays a crucial role in predicting the prevalence of infectious diseases and represents the average number of secondary cases arising from the primary infected person. Rt represents the average number of secondary cases that the primary case may produce at time t. As the development of prevention and control strategies and the implementation of prevention and control measures are different in different parts of the world, the epidemic trends are also significantly different. Estimating the value of R0 and Rt according to the background of different countries and regions is helpful to better predict the global epidemic trend.