TY - JOUR AU - Yom-Tov, Elad AU - Borsa, Diana AU - Cox, Ingemar J AU - McKendry, Rachel A PY - 2014 DA - 2014/06/18 TI -利用互联网数据检测大规模集会中的疾病爆发JO - J Med Internet Res SP - e154 VL - 16 IS - 6kw -大规模集会KW -信息流行病学KW -传染病KW -信息检索KW -数据挖掘AB -背景:音乐节和宗教活动等大规模集会对卫生保健构成挑战,因为有传播传染病的风险。参与者在聚会后很快就会分散,这可能会在他们的社区内传播疾病,从而加剧了这种情况。参与者的分散也对传统的监测方法提出了挑战。因特网的普遍使用可以通过分析用户在事件发生期间和事件发生后不久产生的数据来发现疾病的爆发。目的:这项研究的目的是开发一种算法,可以根据互联网数据,特别是Twitter和搜索引擎查询,对可能爆发的传染病发出警报。方法:我们提取了2012年在英国举行的9个主要音乐节和一个宗教活动(麦加朝觐)中反复提及其中一个的用户在Twitter上发布的所有帖子和在必应搜索引擎上的查询,每次节日之后的30天。我们用三种方法分析了这些数据,其中两种方法比较了节日前后与疾病症状相关的单词,另一种方法比较了节日后英国其他用户使用这些单词的频率。结果:数据平均包括12163名用户发布的750万条推文,以及1756名用户在每个节日发布的32143条查询。我们的方法表明,在9个节日中的两个有统计学意义的疾病症状的出现。 For example, cough was detected at higher than expected levels following the Wakestock festival. Statistically significant agreement (chi-square test, P<.01) between methods and across data sources was found where a statistically significant symptom was detected. Anecdotal evidence suggests that symptoms detected are indeed indicative of a disease that some users attributed to being at the festival. Conclusions: Our work shows the feasibility of creating a public health surveillance system for mass gatherings based on Internet data. The use of multiple data sources and analysis methods was found to be advantageous for rejecting false positives. Further studies are required in order to validate our findings with data from public health authorities. SN - 1438-8871 UR - //www.mybigtv.com/2014/6/e154/ UR - https://doi.org/10.2196/jmir.3156 UR - http://www.ncbi.nlm.nih.gov/pubmed/24943128 DO - 10.2196/jmir.3156 ID - info:doi/10.2196/jmir.3156 ER -
Baidu
map