论文部分内容阅读
手足口病是一种常见的传染病,以往的研究表明该疾病与气象、环境和社会经济等因素相关联,其影响关系复杂,而疾病本身体现出较强的区域聚集性,采用普通的线性风险建模方法无法捕捉影响因素的复杂性及空间聚集性。因此,本文以山东省为例,在前人研究的基础上,提出了采用贝叶斯网络综合风险建模方法研究手足口病的发病风险与气象、土地利用、社会经济及空气污染等要素间的关系,并通过引入空间扫描统计聚集结果,将空间聚集引入到贝叶斯网络模型加强其空间推理功能,减少模型的偏差,提高评估的精度。结果表明,本文建立的手足口病空间贝叶斯网络风险模型具有较高的估计效果,引入的空间聚集性较好地融入到贝叶斯概率推理模型中,合理建立预测因子同手足口病发病风险之间的关系。通过对建模结果的解译,分析了手足口病的发病风险影响因素,特别是气候、社会经济及空气污染的影响。本文的空间贝叶斯建模方法及研究结果对手足口病暴发的防控预警具有重要的意义。
Hand-foot-mouth disease is a common contagious disease. Previous studies have shown that the disease is related to meteorological, environmental and socio-economic factors and has a complex relationship. However, the disease manifests itself as a strong regional aggregation. The common linear Risk modeling methods fail to capture the complexity and spatial aggregation of influencing factors. Therefore, this paper takes Shandong Province as an example. Based on the previous studies, this paper proposes Bayesian Network Risk Modeling to study the relationship between the risk of hand-foot-mouth disease and weather, land use, socioeconomic and air pollution By introducing the results of spatial scanning statistical aggregation, the spatial aggregation is introduced into the Bayesian network model to enhance its spatial reasoning function, reduce the deviation of the model and improve the accuracy of the evaluation. The results show that the Bayesian network risk model of hand, foot and mouth disease established in this paper has a high estimation effect, and the spatial aggregation introduced into the model is well integrated into the Bayesian Probabilistic Reasoning Model to reasonably establish the predictor of hand foot and mouth disease The relationship between risk. Through the interpretation of the modeling results, the influencing factors of HFMD risk are analyzed, especially the influence of climate, socio-economy and air pollution. The method of space Bayesian modeling and the results of this paper are of great significance to prevention and control of hand-foot-mouth disease outbreaks.