摘要
谷歌流感预测(Google Flu Trends,GFT)是大数据在公共卫生领域的首次尝试,白2009年上线以来,受到了各方的广泛关注。上线初期,GFT预测结果与美国CDC数据高度相关,但随后GFT未能预测到2009年甲流大流行,并在2012-2014年季度持续高估了美国流感的流行态势。自2009年以来,GFT模型经过3次升级,其预测偏差得到了有效纠正。本文综述了GFT模型预测流感的原理,模型升级的策略,及其对公共卫生的意义。
Google Flu Trends (GFT) was the first application of big data in the public health field. GFT was open online in 2009 and attracted worldwide attention immediately. However, GFT failed catching the 2009 pandemic H1N1 and kept overestimating the intensity of influenza-like illness in the 2012-2014 season in the United States. GFT model has been updated for three times since 2009, making its prediction bias controlled. Here, we summarized the mechanism GFT worked, the strategy GFT used to update, and its influence on public health.
出处
《中华预防医学杂志》
CAS
CSCD
北大核心
2015年第6期581-584,共4页
Chinese Journal of Preventive Medicine
关键词
公共卫生
预测
大数据
谷歌流感预测
Public health
Forecasting
Big data
Google Flu Trends