Using electronic health records and Internet search information for accurate influenza forecasting.
Using electronic health records and Internet search information for accurate influenza forecasting.
复制标题
DOI：
10.1186/s12879-017-2424-7
复制
发表时间：
2017-05-08
影响因子：
3.7
通讯作者：
Kou SC
中科院分区：
文献类型：
--
作者：
Yang S;Santillana M;Brownstein JS;Gray J;Richardson S;Kou SC
准确的流感活动预测有助于公共卫生官员为不寻常的流感活动准备和分配资源。传统的流感监测系统，如美国疾病控制和预防中心（CDC）的流感样疾病报告，滞后于实时一到两周，而基于云的电子健康记录（EHR）和互联网用户搜索活动中包含的信息通常是近实时的。我们提出了一种方法，将这两个数据源的信息与历史流感活动相结合，在CDC流感报告发布前4周为美国制作全国流感预测。我们扩展了一种最初设计用于使用Google搜索跟踪流感的方法，称为ARGO，将来自EHR和Internet搜索的联合收割机信息与历史流感活动相结合。我们的正则化多元回归模型每周动态选择最适合流感预测的变量。该模型使用包括均方根误差（RMSE）在内的多个指标对2013-2016年期间的流感季节进行评估。我们的方法减少了RMSE的公开可用的替代方法（健康地图flutrends）的33%，20%，17%和21%，为四个时间范围：实时，一，两个，和3个星期前，分别。这种准确性的提高在5%的水平上具有统计学意义。我们的实时估计正确地确定了所研究的流感季节的高峰时间和规模。与历史上公开的基于互联网的预测系统相比，我们的方法显着降低了预测误差，表明：（1）联合收割机数据源的方法与数据质量一样重要;（2）有效地从基于云的EHR和互联网搜索活动中提取信息，可以准确预测流感。本文的在线版本（doi：10.1186/s12879-017-2424-7）包含补充材料，可供授权用户使用。
Accurate influenza activity forecasting helps public health officials prepare and allocate resources for unusual influenza activity. Traditional flu surveillance systems, such as the Centers for Disease Control and Prevention’s (CDC) influenza-like illnesses reports, lag behind real-time by one to 2 weeks, whereas information contained in cloud-based electronic health records (EHR) and in Internet users’ search activity is typically available in near real-time. We present a method that combines the information from these two data sources with historical flu activity to produce national flu forecasts for the United States up to 4 weeks ahead of the publication of CDC’s flu reports. We extend a method originally designed to track flu using Google searches, named ARGO, to combine information from EHR and Internet searches with historical flu activities. Our regularized multivariate regression model dynamically selects the most appropriate variables for flu prediction every week. The model is assessed for the flu seasons within the time period 2013–2016 using multiple metrics including root mean squared error (RMSE). Our method reduces the RMSE of the publicly available alternative (Healthmap flutrends) method by 33, 20, 17 and 21%, for the four time horizons: real-time, one, two, and 3 weeks ahead, respectively. Such accuracy improvements are statistically significant at the 5% level. Our real-time estimates correctly identified the peak timing and magnitude of the studied flu seasons. Our method significantly reduces the prediction error when compared to historical publicly available Internet-based prediction systems, demonstrating that: (1) the method to combine data sources is as important as data quality; (2) effectively extracting information from a cloud-based EHR and Internet search activity leads to accurate forecast of flu. The online version of this article (doi:10.1186/s12879-017-2424-7) contains supplementary material, which is available to authorized users.