%0期刊文章%@ 1438-8871 %I JMIR出版物%V 19 卡塔尔世界杯8强波胆分析%N 11 %P e370 %T使用搜索趋势的季节性流感分区域Nowcasts %A Kandula,Sasikiran %A Hsu,Daniel %A Shaman,Jeffrey %+哥伦比亚大学环境卫生科学系，ARB大楼，11楼，西168街722号，纽约，10032，美国，1 2123053590，sk3542@cumc.columbia.edu %K人流感%K分类和回归树%K nowcasts %K信息流行病学%K信息监测%K监测%D 2017年%7 06.11.2017年%9原始论文%J J医学Internet Res %G英文%X背景:在州或城市一级限制季节性流感暴发的不利影响需要密切监测局部疫情并对其进展进行可靠预测。尽管流感或流感样疾病(ILI)的预测模型越来越可用，但由于无法在局部尺度上实时观测当前疫情状态，其对局部疫情的适用性受到限制。由各个卫生部门收集的监测数据被广泛接受为估计疫情状态的参考标准，在缺乏监测数据的情况下，使用基于web的活动(如搜索引擎查询、推文和访问与卫生相关的网页)构建的临近预报代理可能很有用。谷歌流感趋势(GFT)之前发布了州和市ILI的Nowcast估计;然而，这些估计的验证很少被报道。目的:本研究的目的是建立并验证分区域地理尺度的ILI近预报模型。方法:基于自回归(自回归综合移动平均;ARIMA)和监督回归方法(随机森林)在美国州一级使用区域加权ILI和基于web的搜索活动，这些搜索活动源自谷歌的扩展趋势应用程序编程接口。我们使用50个州六个季节的实际监测数据验证了这些方法的性能。 We also built state-level nowcast models using state-level estimates of ILI and compared the accuracy of these estimates with the estimates of the regional models extrapolated to the state level and with the nowcast estimates published by GFT. Results: Models built using regional ILI extrapolated to state level had a median correlation of 0.84 (interquartile range: 0.74-0.91) and a median root mean square error (RMSE) of 1.01 (IQR: 0.74-1.50), with noticeable variability across seasons and by state population size. Model forms that hypothesize the availability of timely state-level surveillance data show significantly lower errors of 0.83 (0.55-0.23). Compared with GFT, the latter model forms have lower errors but also lower correlation. Conclusions: These results suggest that the proposed methods may be an alternative to the discontinued GFT and that further improvements in the quality of subregional nowcasts may require increased access to more finely resolved surveillance data. %M 29109069 %R 10.2196/jmir.7486 %U //www.mybigtv.com/2017/11/e370/ %U https://doi.org/10.2196/jmir.7486 %U http://www.ncbi.nlm.nih.gov/pubmed/29109069