Spatiotemporal prediction of infectious diseases using structured Gaussian processes with application to Crimean-Congo hemorrhagic fever.
Spatiotemporal prediction of infectious diseases using structured Gaussian processes with application to Crimean-Congo hemorrhagic fever.
复制标题
DOI：
10.1371/journal.pntd.0006737
复制
发表时间：
2018-08
影响因子：
3.8
通讯作者：
Gönen M
中科院分区：
文献类型：
--
作者：
Ak Ç;Ergönül Ö;Şencan İ;Torunoğlu MA;Gönen M
传染病是全世界主要的医疗保健问题之一，每年导致数百万人死亡。为了制定有效的控制和预防策略，我们需要可靠的计算工具来了解疾病动态并预测未来的病例。政策制定者可以使用这些计算工具做出更明智的决策。在这项研究中，我们开发了一个基于高斯过程的计算框架来执行传染病的时空预测，并在我们的公式中利用相似矩阵的特殊结构来获得非常有效的实现。然后，我们针对 2004 年至 2015 年土耳其克里米亚-刚果出血热病例建模问题测试了我们的框架。我们表明，在时间、空间和时空预测场景下，我们的高斯过程公式比两种常用的标准机器学习算法（即随机森林和增强回归树）获得了更好的结果。这些结果表明，我们的框架有潜力为公共卫生政策制定者做出重要贡献。传染病在全世界范围内造成严重的健康问题，并给公共卫生政策制定者带来艰巨的挑战。这就是为什么他们需要可靠的计算工具来更好地了解疾病并预测病例数。他们将受益于此类计算工具，在制定控制和预防策略时做出更明智的决策。我们制定了一个计算框架，可用于模拟传染病的空间、时间或时空动态。我们展示了我们的框架在土耳其克里米亚-刚果出血热建模问题上的实用性。
Infectious diseases are one of the primary healthcare problems worldwide, leading to millions of deaths annually. To develop effective control and prevention strategies, we need reliable computational tools to understand disease dynamics and to predict future cases. These computational tools can be used by policy makers to make more informed decisions. In this study, we developed a computational framework based on Gaussian processes to perform spatiotemporal prediction of infectious diseases and exploited the special structure of similarity matrices in our formulation to obtain a very efficient implementation. We then tested our framework on the problem of modeling Crimean–Congo hemorrhagic fever cases between years 2004 and 2015 in Turkey. We showed that our Gaussian process formulation obtained better results than two frequently used standard machine learning algorithms (i.e., random forests and boosted regression trees) under temporal, spatial, and spatiotemporal prediction scenarios. These results showed that our framework has the potential to make an important contribution to public health policy makers. Infectious diseases cause important health problems worldwide and create difficult challenges for public health policy makers. That is why they need reliable computational tools to better understand disease and to predict case counts. They will benefit from such computational tools to make more informed decisions in developing control and prevention strategies. We formulated a computational framework that can be used to model spatial, temporal, or spatiotemporal dynamics of infectious diseases. We showed the utility of our framework on the problem of modeling Crimean–Congo hemorrhagic fever in Turkey.
登录
查看更多内容
影响因子：
1.7
作者：
Ducheyne, Els;Charlier, Johannes;Hendrickx, Guy
通讯作者：
Hendrickx, Guy
影响因子：
64.8
作者：
Jones KE;Patel NG;Levy MA;Storeygard A;Balk D;Gittleman JL;Daszak P
通讯作者：
Daszak P
影响因子：
8.4
作者：
Ince, Yavuz;Yasa, Cagla;Ergonul, Onder
通讯作者：
Ergonul, Onder
影响因子：
1.8
作者：
Friedman, JH
通讯作者：
Friedman, JH
影响因子：
3.9
作者：
Bhatt, Samir;Cameron, Ewan;Gething, Peter W.
通讯作者：
Gething, Peter W.